Salade composée Clipart
Food & Drink
· by ysabeau
⬇ Download SVG
⧉ Copy SVG (paste into Figma)
✓ Free download - no signup, no watermark
CC0 (Public Domain)
CC0 Public Domain - free for personal and commercial use, no attribution required.
License deed →
Salade composée - ysabeau (CC0 (Public Domain)), via Clipart.Free
{'account_label': 'Account', 'total_credits': 'Credits', 'plan_subscribed': 'Plan', 'next_billing_date': 'Next billing date', 'cancel_subscription': 'Cancel Subscription', 'plan_not_active': 'Plan not active', 'api_token': 'API Token', 'get_credits': 'Get Credits', 'hello': 'Hello', 'change_password': 'Change Password', 'delete_account': 'Delete Account', 'billing_history': 'Billing History', 'status': 'Status', 'processor': 'Processor', 'amount': 'Amount', 'date': 'Date', 'no_payments': 'No payments yet', 'are_you_sure': 'Are you sure you want to cancel your subscription?', 'close': 'Close', 'success': 'Success!', 'success_message': 'Your action was completed successfully.', 'back_to_home': 'Back to Home', 'about_h1': 'About transcribe.free', 'start_transcribing': 'Start transcribing', 'verify_email': 'Verify Email', 'verify_email_subtitle': 'Enter the code we sent to your email', 'verification_code': 'Verification Code', 'no_email': "Didn't receive the email?", 'resend_email': 'Resend', 'contact': 'Contact Us', 'need_help': 'Need help?', 'request_refund': 'Request Refund', 'message_sent': "Your message has been sent. We'll get back to you soon.", 'email_address': 'Email Address', 'message': 'Message', 'send': 'Send', 'or_contact': 'Or email us directly', 'lost_password': 'Forgot Password', 'lost_password_subtitle': "Enter your email and we'll send you a reset link", 'remember_password': 'Remember your password?', 'login': 'Login', 'sign_up': 'Sign Up', 'password': 'Password', 'password_hint': 'Minimum 4 characters', 'already_have_account': 'Already have an account?', 'forgot_password': 'Forgot password?', 'dont_have_account': "Don't have an account?", 'privacy_policy': 'Privacy Policy', 'refund_policy': 'Refund Policy', 'transaction_id': 'Transaction ID', 'payment_email': 'Email used for payment', 'pricing_h1': 'Simple pricing, serious free tier', 'pricing_sub': 'The free tier is the most generous on the market. Pay only when your files outgrow it.', 'payments_soon': 'Payments are launching soon — the free tier is fully open today.', 'plan_free': 'Free', 'plan_free_sub': 'No account needed', 'most_popular': 'Most popular', 'plan_pro_annual': 'Pro Annual', 'billed_annually': '$60 billed yearly', 'go_pro_annual': 'Go Pro — $60/yr', 'payments_soon_short': 'Payments launching soon', 'plan_pro_monthly': 'Pro Monthly', 'cancel_anytime': 'Cancel anytime', 'go_pro_monthly': 'Go Pro — $10/mo', 'packs_heading': 'Credit packs — one-time, never expire', 'packs_sub': '1 credit = 1 minute of audio, rounded up per file. For one-off interviews and back catalogs — no subscription.', 'pack_s': 'Pack S', 'pack_m': 'Pack M', 'pack_l': 'Pack L', 'minutes_label': 'minutes', 'pack_features': '10-hour files, speaker labels, priority queue', 'buy_label': 'Buy', 'soon_label': 'Soon', 'compare_tiers': 'Compare tiers', 'tier_anon': 'No sign-up', 'tier_free': 'Free account', 'tier_pro': 'Pro', 'tier_packs': 'Credit packs', 'row_files': 'Files', 'row_length': 'Per-file length', 'row_size': 'Per-file size', 'row_queue': 'Queue', 'row_speakers': 'Speaker labels', 'row_exports': 'Exports', 'row_history': 'History', 'api_note': 'Need a developer API for speech-to-text?', 'faq_heading': 'Frequently asked questions', 'reset_password': 'Reset Password', 'repeat_password': 'Confirm Password', 'payments_soon_title': 'Payments are launching soon', 'payments_soon_body': "We're finishing payment setup for transcribe.free. The free tier is fully open in the meantime — 3 files a day with no account, 5 a day with a free one.", 'checkout_loading_payment': 'Loading secure payment form…', 'mo': 'mo', 'checkout_or': 'or', 'checkout_wallet_loading': 'Checking for Apple Pay / Google Pay…', 'payment_secured': 'Secure payment via', 'crypto': 'Pay with Crypto', 'crypto_not_available': 'Cryptocurrency payment not available for this plan', 'tools': 'Tools', 'audio_to_text': 'Audio to Text', 'video_to_text': 'Video to Text', 'mp3_to_text': 'MP3 to Text', 'mp4_to_text': 'MP4 to Text', 'srt_generator': 'SRT Generator', 'languages_label': 'Languages', 'lang_spanish': 'Spanish', 'lang_french': 'French', 'lang_german': 'German', 'lang_portuguese': 'Portuguese', 'lang_japanese': 'Japanese', 'lang_chinese': 'Chinese', 'lang_arabic': 'Arabic', 'lang_hindi': 'Hindi', 'lang_korean': 'Korean', 'lang_italian': 'Italian', 'pricing': 'Pricing', 'logout': 'Logout', 'footer_tagline': 'Free AI transcription with no sign-up, no watermark, and no email gate. Files auto-delete after 24 hours.', 'company': 'Company', 'about_us': 'About', 'terms_of_service': 'Terms of Service', 'refund': 'Refund Policy', 'home_h1_accent': 'in minutes.', 'trust_no_signup': 'No sign-up', 'trust_no_watermark': 'No watermark', 'trust_exports': 'TXT · SRT · VTT exports', 'trust_autodelete': 'Files auto-delete in 24h', 'dz_title': 'Drag & drop your file here', 'dz_or': 'or', 'dz_browse': 'browse your files', 'dz_free_limits': 'Free: {0} files a day · up to {1} min & {2} MB each', 'lang_locked_note': 'Language pre-set for this page', 'spoken_language': 'Spoken language', 'autodetect': 'Auto-detect', 'upload_note_pre': 'Bigger files or more uploads?', 'upload_note_signup': 'Free account: 5 files/day, 1-hour files', 'upload_note_pro': 'Pro: 10-hour files + speaker labels', 'uploading': 'Uploading…', 'uploading_hint': "Keep this tab open — you'll be redirected to your transcript.", 'checkout_stripe_blocked': 'Payment system could not load. Please disable your ad blocker or content blocker for this page, then refresh.', 'transcribing_title': 'Transcribing your file', 'step_uploaded': 'Uploaded', 'step_queued': 'Queued', 'step_transcribing': 'Transcribing', 'step_ready': 'Ready', 'progress_note': 'Usually takes a fraction of the audio length. This page updates automatically.', 'duration_label': 'Duration', 'failed_title': 'Transcription failed', 'failed_no_charge': 'No credits were charged for this file.', 'try_again': 'Try again', 'anon_banner': 'Saved for 24 hours — sign up free to keep it.', 'anon_banner_cta': 'Create a free account', 'language_label': 'Language', 'segments_label': 'segments', 'delete_label': 'Delete', 'timestamps_label': 'Timestamps', 'copy_all': 'Copy all', 'export_label': 'Export', 'feature_no_ads': 'No advertisements', 'feature_unlimited': 'Unlimited usage', 'feature_priority': 'Priority support', 'feature_early_access': 'Early access to new features', 'tp_audio_to_text_faq5_q': 'How long can my audio file be?', 'your_transcripts': 'Your Transcripts', 'file_label': 'File', 'status_completed': 'Ready', 'status_failed': 'Failed', 'status_processing': 'Processing', 'no_transcripts_yet': 'No transcripts yet.', 'not_found_message': "That page doesn't exist — but the transcriber does.", 'failed_help': 'Keeps failing?', 'words_label': 'words', 'new_transcription': 'New transcription', 'share_link': 'Share link', 'audio_follow_note': 'Playback follows the transcript — click any timestamp to jump.', 'export_nudge': 'Exported! This transcript disappears in 24 hours —', 'export_nudge_cta': 'sign up free to keep a saved library', 'meeting_transcription': 'Meeting Transcription', 'interview_transcription': 'Interview Transcription', 'tp_home_title': 'Free Audio & Video Transcription — No Sign-Up | transcribe.free', 'tp_home_desc': 'Turn audio or video into accurate text in minutes. Free, no account needed — 3 files a day, up to 30 minutes each. Export TXT, SRT, VTT. Files deleted after 24 hours.', 'tp_home_h1': 'Free Audio & Video Transcription', 'tp_home_sec0_h': 'Why this transcriber is actually free', 'tp_home_sec0_p0': 'Almost every transcription tool gates your transcript behind an account, a watermark, or an email form. This one does not: anonymous visitors get 3 files a day, up to 30 minutes and 100 MB each, with full TXT, SRT, and VTT exports. We run our own GPU servers, so short files cost us almost nothing to process — the free tier is the product, and paid plans for long files (up to 10 hours) pay for it.', 'tp_home_sec0_p1': 'A free account raises the limits to 5 files a day at up to 1 hour each and saves your transcript library. Pro adds priority processing, speaker labels, and DOCX/PDF exports.', 'tp_home_sec1_h': 'Built for real recordings', 'tp_home_sec1_p0': 'The engine is a Whisper-class large speech model — the same family of models used by professional transcription services. It handles meetings, lectures, podcasts, interviews, voice memos, and phone recordings in 90+ languages with automatic language detection, and it punctuates and cases text properly so the transcript reads like writing, not like subtitles glued together.', 'tp_home_sec1_p1': 'After processing you land in a transcript editor: click any line to fix it, search the text, toggle timestamps, then export in one click.', 'tp_home_faq0_q': "Is it really free? What's the catch?", 'tp_home_faq0_a': "The free tier is exactly what it says: 3 files a day per visitor, up to 30 minutes and 100 MB per file, with no account, no watermark, and no email gate. The catch is only the per-file length cap — longer files (lectures, podcasts, full meetings) need a free account (1-hour files) or Pro / a credit pack (10-hour files). That's the whole business model.", 'tp_home_faq1_q': 'Do I need an account?', 'tp_home_faq1_a': 'No. Drop a file and you get the transcript and all three core exports (TXT, SRT, VTT) without signing up. An account is optional: it raises the daily and per-file limits and keeps your transcripts in a library instead of auto-deleting them.', 'tp_home_faq2_q': 'What happens to my file after I upload it?', 'tp_home_faq2_a': 'Anonymous uploads and their transcripts are automatically deleted 24 hours after upload — treat the transcript link as temporary and export what you need. We never use your audio to train models, and files are not shared with any third party; processing happens on our own GPU servers.', 'tp_home_faq3_q': 'How accurate is the transcription?', 'tp_home_faq3_a': 'On clear speech with a decent microphone, a Whisper-class large model is near-human — typically a low single-digit word error rate in English and other well-supported languages. Accuracy drops with heavy background noise, crosstalk, strong accents, or very quiet recordings, which is why every transcript opens in an editor for quick fixes.', 'tp_home_faq4_q': 'How long does it take?', 'tp_home_faq4_a': 'Usually a fraction of the audio length: a 10-minute recording typically transcribes in about a minute once processing starts. At busy times your file may briefly queue — the progress page shows the live status, and Pro jobs skip to the priority queue.', 'tp_home_faq5_q': 'Which file types can I upload?', 'tp_home_faq5_a': 'Audio: MP3, WAV, M4A, FLAC, OGG, AAC, WMA, Opus, AIFF, AMR. Video: MP4, MOV, MKV, WebM, AVI, WMV, MPEG, 3GP. For video we read only the audio track, so resolution and file size matter far less than duration.', 'tp_audio_to_text_title': 'Audio to Text — Free AI Converter, No Sign-Up | transcribe.free', 'tp_audio_to_text_desc': 'Convert audio to text free with AI. MP3, WAV, M4A, FLAC and more — no account, 3 files a day, up to 30 minutes each. Edit, then export TXT, SRT or VTT.', 'tp_audio_to_text_h1': 'Convert Audio to Text', 'tp_audio_to_text_sub': 'Upload any common audio format and get an accurate, editable transcript. Free with no sign-up — export TXT, SRT, or VTT.', 'tp_audio_to_text_sec0_h': 'Every common audio format, one transcriber', 'tp_audio_to_text_sec0_p0': 'This page accepts the audio formats people actually have: MP3 and AAC from podcasts and downloads, WAV and AIFF from recording gear, M4A from iPhone and Android voice memo apps, FLAC from archival rips, OGG and Opus from messaging apps, and WMA from older Windows recorders. There is no separate converter step — the transcriber decodes the file itself, so you never need to convert WAV to MP3 first.', 'tp_audio_to_text_sec0_p1': 'Language is auto-detected across 90+ languages, or you can pin it in the options if your recording mixes languages and detection guesses wrong.', 'tp_audio_to_text_sec1_h': 'From recording to usable text', 'tp_audio_to_text_sec1_p0': 'Once processed, the transcript opens in an editor with per-sentence timestamps. Click any line to correct it, search for a phrase, then export: TXT for documents and notes, SRT or VTT if the audio belongs under a video. Signed-in users also get DOCX and PDF for sharing polished documents.', 'tp_audio_to_text_faq0_q': 'Which audio formats are supported?', 'tp_audio_to_text_faq0_a': 'MP3, WAV, M4A, FLAC, OGG, AAC, WMA, Opus, AIFF, and AMR. If your recorder produces something rarer, converting to WAV or MP3 first with any free converter will always work — but try the original first; the decoder covers most containers.', 'tp_audio_to_text_faq1_q': 'Will noisy or low-quality recordings work?', 'tp_audio_to_text_faq1_a': 'Usually, with caveats. The model is trained on a lot of imperfect real-world audio, so hiss, room echo, and compression artifacts rarely break it. What genuinely hurts accuracy is speech that is quiet relative to the noise — a recorder far from the speaker, or music louder than the voice. If you can, record closer to the source; the editor makes fixing the remaining errors quick.', 'tp_audio_to_text_faq2_q': 'Can it handle multiple speakers on one track?', 'tp_audio_to_text_faq2_a': "Yes — everyone's words are transcribed regardless of how many people speak. On the free tier the transcript doesn't say who said what; speaker labels (diarization) are a Pro feature that tags each segment SPEAKER 1, SPEAKER 2, etc., and lets you rename them in the editor.", 'tp_audio_to_text_faq3_q': 'Do I get timestamps?', 'tp_audio_to_text_faq3_a': 'Yes. Every segment carries start and end times. In the editor you can toggle timestamp display on or off, and the SRT/VTT exports embed them in standard subtitle timing format. The TXT export is clean prose without timestamps.', 'tp_audio_to_text_faq4_q': 'Can I edit the transcript before exporting?', 'tp_audio_to_text_faq4_a': "Yes — that's the default workflow. The transcript opens in an editor where each segment is click-to-edit with autosave. Fix names, jargon, or misheard words, then export; your edits are included in every format.", 'tp_audio_to_text_faq5_a': 'Anonymous: 30 minutes / 100 MB per file, 3 files a day. Free account: 1 hour / 500 MB, 5 files a day. Pro or a credit pack: up to 10 hours and 5 GB per file. Duration is what matters — a long, small MP3 hits the cap before a short, huge WAV does.', 'tp_video_to_text_title': 'Video to Text — Free AI Transcription, No Sign-Up | transcribe.free', 'tp_video_to_text_desc': 'Transcribe video to text free. MP4, MOV, MKV, WebM and more — audio is extracted server-side, nothing re-encoded. No account needed. Export TXT, SRT, VTT.', 'tp_video_to_text_h1': 'Convert Video to Text', 'tp_video_to_text_sub': 'Upload a video, we pull the audio track and transcribe it. Subtitles (SRT/VTT) or a plain transcript — free, no sign-up.', 'tp_video_to_text_sec0_h': 'How video transcription works here', 'tp_video_to_text_sec0_p0': 'When you upload a video, the server reads just the audio stream out of the container — your video is never re-encoded, resized, or altered, and the picture content is never analyzed. That makes the process fast even for big files: a 2 GB screen recording with 20 minutes of speech transcribes as quickly as a 20-minute MP3.', 'tp_video_to_text_sec0_p1': 'The result is a timestamped transcript you can export as SRT or VTT subtitle files ready for YouTube, Premiere, Resolve, or an HTML5 player — or as plain TXT when you just need the words.', 'tp_video_to_text_sec1_h': 'Meetings, screen recordings, lectures, footage', 'tp_video_to_text_sec1_p0': 'Typical uploads here are Zoom and Teams recordings, OBS screen captures, lecture recordings, and phone footage. All of these carry compressed AAC audio that the model handles well. If a video has several audio tracks (some screen recorders save mic and system audio separately), the first track is used — export with tracks merged if you need both sides of a call.', 'tp_video_to_text_faq0_q': 'How is the audio extracted from my video?', 'tp_video_to_text_faq0_a': "Server-side, with a standard demuxer: we read the existing audio stream out of the container without re-encoding the video. Your file isn't converted, compressed, or watermarked — the video track is simply ignored, and only the speech is analyzed.", 'tp_video_to_text_faq1_q': 'Which video containers are supported?', 'tp_video_to_text_faq1_a': 'MP4, MOV, MKV, WebM, AVI, WMV, MPEG/MPG, and 3GP. That covers phone videos (MP4/MOV), screen recorders (MKV/MP4/WebM), meeting-app downloads (MP4), and most camera footage. If you have something exotic, remuxing to MP4 with any free tool will do it.', 'tp_video_to_text_faq2_q': 'Do you keep my video?', 'tp_video_to_text_faq2_a': "Anonymous uploads are deleted automatically 24 hours after upload — the video file and the transcript both. Account uploads stay in your library until you delete them. Either way the video is only ever stored to be transcribed; it isn't used for training or shared anywhere.", 'tp_video_to_text_faq3_q': 'Should I export a transcript or subtitles?', 'tp_video_to_text_faq3_a': 'Both come from the same result. Choose TXT when you want readable prose — meeting notes, quotes, an article draft. Choose SRT or VTT when the text goes back under the video: SRT for YouTube uploads and most editors, VTT for web players. You can download all of them from the same editor.', 'tp_video_to_text_faq4_q': 'My video file is huge — any tips?', 'tp_video_to_text_faq4_a': 'Duration is the real limit, not gigabytes, but upload time is on you. If your connection is slow, extract the audio first (most editors export audio-only in seconds) and upload that instead — a 60 MB M4A uploads far faster than the 4 GB video it came from, and the transcript is identical.', 'tp_video_to_text_faq5_q': 'What about videos with loud music beds?', 'tp_video_to_text_faq5_a': 'Speech over a moderate music bed usually transcribes fine — the model is good at focusing on the voice. Where it struggles is music louder than the speech, heavy ducking, or sung lyrics mixed with dialogue. Expect to fix more in the editor on those sections.', 'tp_mp3_to_text_title': 'MP3 to Text — Free AI Converter, No Sign-Up | transcribe.free', 'tp_mp3_to_text_desc': 'Turn MP3 into accurate text in minutes. Free, no account needed — 3 files a day, up to 30 minutes each. Export TXT, SRT, VTT. Files deleted after 24 hours.', 'tp_mp3_to_text_h1': 'Convert MP3 to Text', 'tp_mp3_to_text_sub': 'The most common audio format, transcribed free. Podcasts, voice memos, interviews — drop the MP3, edit the text, export.', 'tp_mp3_to_text_sec0_h': 'Why MP3 is the easy case', 'tp_mp3_to_text_sec0_p0': 'MP3 is what most spoken audio already lives in: podcast downloads, voice recorder apps, old archives, exported calls. The model was trained on enormous amounts of compressed speech, so the MP3 codec itself costs essentially nothing in accuracy — a clean 64 kbps mono voice recording transcribes as well as a studio WAV.', 'tp_mp3_to_text_sec0_p1': 'Upload the file as-is. There is no need to convert, re-encode, or "improve" an MP3 before transcribing; re-encoding can only lose information.', 'tp_mp3_to_text_sec1_h': 'From MP3 to notes, quotes, and subtitles', 'tp_mp3_to_text_sec1_p0': 'A 30-minute podcast episode fits the anonymous free tier; a full-length episode or a 2-hour interview needs a free account (1 hour) or Pro (10 hours). After processing, use the editor to fix names and jargon, then export TXT for notes and quotes or SRT/VTT if the audio will be published with video.', 'tp_mp3_to_text_faq0_q': 'Does a low MP3 bitrate hurt accuracy?', 'tp_mp3_to_text_faq0_a': 'Barely, for speech. Anything from 64 kbps mono upward transcribes essentially as well as lossless audio — phone voice memos and podcast downloads are well above that. Below ~32 kbps you may see more errors on names and fast speech, but even old dictaphone-quality MP3s usually come out readable.', 'tp_mp3_to_text_faq1_q': 'Can I transcribe a whole podcast episode?', 'tp_mp3_to_text_faq1_a': 'Yes. A 30-minute episode fits the no-signup tier. Typical 45–90 minute episodes fit the free-account tier (up to 1 hour) or Pro (up to 10 hours). Transcribing your back catalog in bulk is what the credit packs are for — $5 covers 10 hours of audio, one-time, no subscription.', 'tp_mp3_to_text_faq2_q': 'Do iPhone and Android voice memos work?', 'tp_mp3_to_text_faq2_a': 'Yes. iPhone Voice Memos exports M4A and most Android recorders export MP3 or M4A — both upload here directly, no conversion needed. Memos recorded in a pocket or across a room will have more errors than ones recorded near the speaker; the editor makes cleanup fast.', 'tp_mp3_to_text_faq3_q': 'Can it transcribe song lyrics from an MP3?', 'tp_mp3_to_text_faq3_a': 'Sometimes, but set expectations: the model is built for speech. Clear, front-and-center vocals often come out largely right; anything with dense instrumentation, stacked harmonies, or rap delivery will be patchy. For lyrics specifically, a dedicated lyrics site usually beats any speech-to-text model.', 'tp_mp3_to_text_faq4_q': 'I have dozens of MP3s — can I do them all?', 'tp_mp3_to_text_faq4_a': 'The free tiers are per-day (3 anonymous / 5 with a free account), so bulk jobs need Pro (fair-use unlimited at $10/month) or a credit pack ($5 for 10 hours, $15 for 40 hours, $39 for 150 hours — packs never expire). Each file is one upload; batch upload is on the roadmap.', 'tp_mp3_to_text_faq5_q': 'Are my ID3 tags or the file itself modified?', 'tp_mp3_to_text_faq5_a': 'No. The MP3 is read, transcribed, and (for anonymous uploads) deleted after 24 hours. We never modify, re-tag, or re-encode the file, and the download you get is the transcript — your original stays exactly as uploaded.', 'tp_mp4_to_text_title': 'MP4 to Text — Free AI Transcription, No Sign-Up | transcribe.free', 'tp_mp4_to_text_desc': 'Transcribe MP4 video to text free. Zoom recordings, screen captures, phone video — no account needed, up to 30 min free. Export TXT, SRT, VTT.', 'tp_mp4_to_text_h1': 'Convert MP4 to Text', 'tp_mp4_to_text_sub': 'Zoom calls, screen recordings, phone videos — drop the MP4 and get a timestamped transcript or ready-to-use subtitles.', 'tp_mp4_to_text_sec0_h': 'The meeting-recording workhorse', 'tp_mp4_to_text_sec0_p0': 'MP4 is what Zoom, Teams, Meet, OBS, and every phone camera hand you. Only the audio track inside the MP4 is read — the video stream is ignored entirely, so a 4K hour-long recording transcribes exactly as fast as a 480p one of the same length. Resolution is irrelevant; duration is what counts against your limit.', 'tp_mp4_to_text_sec0_p1': 'That also means the fastest workflow for very large MP4s is extracting the audio first: the transcript is identical and the upload is a fraction of the size.', 'tp_mp4_to_text_sec1_h': 'Subtitles or minutes from the same file', 'tp_mp4_to_text_sec1_p0': 'For published video, export SRT (YouTube, Premiere, Resolve, CapCut) or VTT (HTML5 players, Vimeo). For meetings and lectures, export TXT and you have searchable minutes with the filler stripped out by your own edits. Speaker labels for multi-person calls are available on Pro.', 'tp_mp4_to_text_faq0_q': 'Do Zoom, Teams, and screen recordings work?', 'tp_mp4_to_text_faq0_a': "Yes — meeting-app MP4s are the most common upload on this page. Local and cloud Zoom recordings, Teams downloads, and OBS/QuickTime screen captures all carry standard AAC audio that transcribes well. For multi-speaker calls, Pro's speaker labels tag who said what.", 'tp_mp4_to_text_faq1_q': 'My MP4 has multiple audio tracks — which is used?', 'tp_mp4_to_text_faq1_a': 'The first audio track in the container. Some screen recorders (OBS in particular) can save microphone and system audio as separate tracks — if you need both sides transcribed, export/re-record with tracks merged, or extract and upload the mixed track.', 'tp_mp4_to_text_faq2_q': 'Are iPhone HEVC videos (.mp4/.mov) supported?', 'tp_mp4_to_text_faq2_a': "Yes. iPhone footage — whether H.264 or HEVC video, in .mp4 or .mov — carries AAC audio, and that's all we read. No need to convert the video codec; the audio track is identical either way.", 'tp_mp4_to_text_faq3_q': 'Should I export SRT or TXT from my MP4?', 'tp_mp4_to_text_faq3_a': 'Depends where the text goes. SRT/VTT keep the timing and drop straight onto the video as subtitles or captions. TXT drops the timing and gives you clean prose for notes, documentation, or quoting. Both exports come from the same transcript, so you can grab both.', 'tp_mp4_to_text_faq4_q': 'Why does duration matter more than file size?', 'tp_mp4_to_text_faq4_a': 'Because only the audio is processed. A 3 GB 4K video with 10 minutes of speech is a 10-minute job; a 40 MB voice-only MP4 that runs 2 hours is a 2-hour job. The per-file caps (30 min anonymous, 1 h free account, 10 h paid) are all about duration, with generous size ceilings alongside.', 'tp_mp4_to_text_faq5_q': 'Can I upload 4K files? Is there a size limit?', 'tp_mp4_to_text_faq5_a': 'Yes — 4K is fine and changes nothing about accuracy or speed. Size ceilings: 100 MB anonymous, 500 MB free account, 5 GB Pro/packs. If your 4K file exceeds the ceiling for your tier, extract the audio (tiny by comparison) and upload that instead.', 'tp_srt_generator_title': 'Free SRT Generator — Subtitles from Any Video | transcribe.free', 'tp_srt_generator_desc': 'Generate SRT subtitle files from any video or audio, free. AI transcription with editable timing — no sign-up, no watermark. VTT export included.', 'tp_srt_generator_h1': 'Free SRT Subtitle Generator', 'tp_srt_generator_sub': 'Upload video or audio and download a ready-to-use .srt file — timed, numbered, and editable. VTT included, no sign-up.', 'tp_srt_generator_sec0_h': 'What you get: a proper .srt file', 'tp_srt_generator_sec0_p0': 'An SRT file is plain text with numbered cues: a sequence number, a timing line in HH:MM:SS,mmm --> HH:MM:SS,mmm format, and the caption text. Every editor and platform that accepts subtitles accepts SRT. The generator transcribes your file with AI, splits it into readably short cues, and hands you the .srt — plus a WebVTT (.vtt) version for web players from the same button bar.', 'tp_srt_generator_sec0_p1': 'Before downloading, you can fix any line in the transcript editor; your edits flow straight into the subtitle file.', 'tp_srt_generator_sec1_h': 'SRT vs VTT — which one do you need?', 'tp_srt_generator_sec1_p0': 'SRT is the older, universal format: use it for YouTube uploads, Premiere Pro, DaVinci Resolve, CapCut, and virtually any desktop editor. VTT (WebVTT) is the web-native format: use it for HTML5 <track> captions, Vimeo, and most embedded players. They carry the same text and timing — VTT uses a dot instead of a comma in timestamps and supports web styling. Both exports are free here.', 'tp_srt_generator_faq0_q': 'What exactly is an SRT file?', 'tp_srt_generator_faq0_a': "A plain-text subtitle format: numbered blocks, each with a timing line (00:01:23,450 --> 00:01:26,100) and one or two lines of caption text. Because it's plain text, you can open and tweak it in any editor, and every major video platform and NLE imports it.", 'tp_srt_generator_faq1_q': 'SRT or VTT — which should I download?', 'tp_srt_generator_faq1_a': "SRT for YouTube uploads and desktop editors (Premiere, Resolve, CapCut, Final Cut via converters). VTT for websites: HTML5 <track> elements, Vimeo, and JS players like Video.js or Plyr expect WebVTT. Same content, different dialect — download both if you're not sure.", 'tp_srt_generator_faq2_q': 'How are subtitle line lengths handled?', 'tp_srt_generator_faq2_a': 'Cues are split on sentence and phrase boundaries into short segments rather than paragraph-length blocks, following the readability conventions subtitlers use (roughly 1–2 lines per cue, comfortable reading speed). If a cue still reads long, split or trim it in the editor before exporting.', 'tp_srt_generator_faq3_q': 'Can I fix the timing or text before downloading?', 'tp_srt_generator_faq3_a': "Text, yes — click any segment in the editor, type the fix, and it autosaves; the SRT you download includes your edits. Fine-grained timing nudges are best done in your video editor or a subtitle tool after export, since they're easier against the video preview.", 'tp_srt_generator_faq4_q': 'How do I add the SRT to YouTube, CapCut, or Premiere?', 'tp_srt_generator_faq4_a': 'YouTube: Studio → Subtitles → Add → Upload file, choose "With timing". Premiere Pro: Import the .srt like any asset and drop it on the timeline, or use Text → Captions → Import. CapCut: Text → Captions → Import captions. In all three, the timing carries over automatically.', 'tp_srt_generator_faq5_q': 'What about burned-in vs sidecar subtitles?', 'tp_srt_generator_faq5_a': "An SRT is a sidecar file — a separate track viewers can toggle, and platforms can index and translate. Burned-in (hardcoded) subtitles are rendered into the pixels and can't be turned off. Generate the SRT here, and if you want burned-in captions, import it into your editor and render.", 'tp_meeting_transcription_title': 'Meeting Transcription — Zoom, Teams & Meet, Free | transcribe.free', 'tp_meeting_transcription_desc': 'Turn meeting recordings into searchable minutes. Zoom, Teams, Meet — free, no sign-up, files auto-delete in 24h. Speaker labels on Pro. Export TXT, DOCX, SRT.', 'tp_meeting_transcription_h1': 'Meeting Transcription', 'tp_meeting_transcription_sub': 'Drop a Zoom, Teams, or Meet recording and get searchable, editable minutes. Free, no sign-up — speaker labels available on Pro.', 'tp_meeting_transcription_sec0_h': 'Getting the recording out of your meeting app', 'tp_meeting_transcription_sec0_p0': 'Zoom saves local recordings to Documents/Zoom as MP4 (cloud recordings download from the web portal under Recordings). Teams stores meeting videos in OneDrive or SharePoint — open the recording and use Download. Google Meet saves to the organizer\'s Drive in a "Meet Recordings" folder. All three produce standard MP4s that upload here directly; a typical 45-minute meeting fits the free account tier, and an all-hands marathon fits Pro\'s 10-hour cap.', 'tp_meeting_transcription_sec0_p1': "If your meeting wasn't recorded by the app at all — a conference room, a phone on the table — that works too: any audio or video format is fine, though a microphone near the middle of the table beats one at the end.", 'tp_meeting_transcription_sec1_h': 'From recording to minutes and action items', 'tp_meeting_transcription_sec1_p0': 'A meeting transcript is only useful if you can tell who committed to what. On Pro, speaker labels (diarization) tag every segment SPEAKER 1, SPEAKER 2, and so on — click a label in the editor, rename it once to "Priya" or "Legal", and every segment from that voice updates. Search the transcript for "action", "deadline", or a colleague\'s name, fix anything misheard, then export: TXT for pasting into notes, DOCX for circulating formal minutes.', 'tp_meeting_transcription_sec1_p1': 'Two honesty notes: heavy crosstalk — three people talking over each other — is the hardest thing in speech recognition, and moments like that will need manual cleanup. And confidentiality is handled the boring, verifiable way: anonymous uploads auto-delete within 24 hours, account uploads stay only until you delete them, and nothing is used to train models or shared with third parties.', 'tp_meeting_transcription_faq0_q': 'Where do I find my Zoom / Teams / Meet recording file?', 'tp_meeting_transcription_faq0_a': "Zoom: local recordings land in Documents/Zoom (look for the .mp4, not the .m4a next to it — either works); cloud recordings download from zoom.us → Recordings. Teams: the meeting chat links the recording, stored in the organizer's OneDrive/SharePoint — open and Download. Meet: check the organizer's Google Drive → Meet Recordings folder. Upload the downloaded file here as-is.", 'tp_meeting_transcription_faq1_q': 'Can it tell me who said what?', 'tp_meeting_transcription_faq1_a': "Yes, with speaker labels — a Pro / credit-pack feature. The engine separates voices and tags each segment; you rename the tags once in the editor and the whole transcript updates. Without Pro you still get the full text of everyone's words, just not attributed per person.", 'tp_meeting_transcription_faq2_q': 'How accurate is it on a real multi-person meeting?', 'tp_meeting_transcription_faq2_a': 'Clear turn-taking on a decent mic transcribes near-perfectly. Accuracy drops in the moments meetings are worst at: several people talking at once, someone far from the microphone, laptop-speaker echo. Those stretches are why the transcript opens in an editor — find them with search and fix them in seconds against the audio player.', 'tp_meeting_transcription_faq3_q': 'Are my meetings confidential?', 'tp_meeting_transcription_faq3_a': 'Anonymous uploads and their transcripts auto-delete within 24 hours; account uploads persist only until you delete them. Files are processed on our own GPU servers, never used for model training, and never shared. For board-level material, export what you need and delete the transcript immediately — deletion removes the audio file and every segment.', 'tp_meeting_transcription_faq4_q': 'How long a meeting can I transcribe free?', 'tp_meeting_transcription_faq4_a': '30 minutes per file with no account (3 files a day), 1 hour with a free account (5 a day). A weekly hour-long standup fits the free account exactly; anything longer — half-day workshops, recorded trainings — needs Pro ($10/mo) or a credit pack ($5 covers 10 hours, one-time).', 'tp_meeting_transcription_faq5_q': 'Can I get minutes as a Word document?', 'tp_meeting_transcription_faq5_a': 'Yes — DOCX export is included with any account (and PDF alongside it). With speaker labels on, the DOCX comes out as "[Name] said…" paragraphs, which is 90% of the way to circulated minutes: trim the small talk, bold the decisions, send.', 'tp_interview_transcription_title': 'Interview Transcription — Free for Journalists & Researchers | transcribe.free', 'tp_interview_transcription_desc': 'Transcribe interviews free with AI. Verbatim, editable, exact quotes with timestamps — no sign-up, no watermark. Phone and in-person recordings. TXT, DOCX export.', 'tp_interview_transcription_h1': 'Interview Transcription', 'tp_interview_transcription_sub': 'For journalists, researchers, and hiring teams: verbatim transcripts you can verify against the audio, quote by quote. Free, no sign-up.', 'tp_interview_transcription_sec0_h': 'Verbatim vs clean-read — you choose, in the editor', 'tp_interview_transcription_sec0_p0': 'The model produces a near-verbatim transcript: it keeps the words as spoken but punctuates and cases them properly, and it drops most pure stutters. From there the editor lets you go either direction. For qualitative research and oral history, leave it verbatim — false starts and hedges are data. For a published Q&A, clean-read it: click any answer, tighten the phrasing, and the edit autosaves straight into every export format.', 'tp_interview_transcription_sec0_p1': 'Every segment carries a timestamp, which is the quote-verification workflow: search the transcript for the phrase you want to quote, click its timestamp, and the built-in player jumps the audio to that exact moment so you can confirm the words before they go to print.', 'tp_interview_transcription_sec1_h': 'Recording quality is the whole game', 'tp_interview_transcription_sec1_p0': "An interview is usually two voices, which is the easy case — far easier than a six-person meeting. What actually decides accuracy is the recording setup. In person: put the phone between you, not in your pocket. Phone calls: use your phone's call-recording feature or record the call speaker-out with a second device, and expect the callee's side to be slightly harder for the model than yours. Video calls: record locally rather than relying on the platform's compressed cloud audio when you can.", 'tp_interview_transcription_sec1_p1': "One thing this page won't do is legal advice, but know the basics: consent requirements for recording conversations vary by jurisdiction (one-party vs all-party consent), and professional codes usually expect you to tell your subject they're being recorded. Get consent on the recording itself — it's then in the transcript too.", 'tp_interview_transcription_faq0_q': 'Is the transcript verbatim or cleaned up?', 'tp_interview_transcription_faq0_a': 'Near-verbatim by default: the words as spoken, with punctuation and casing added, and most stutter repetitions dropped. Filler words like "um" are sometimes kept, sometimes dropped — if strict verbatim matters for your methodology, do a listen-through pass with the segment player and restore them where they carry meaning.', 'tp_interview_transcription_faq1_q': 'How do I verify a quote before publishing it?', 'tp_interview_transcription_faq1_a': "Search the transcript for the phrase, click the segment's timestamp, and the audio player jumps to that moment. You hear the exact delivery — including the sarcasm or hesitation a transcript can't carry — and can fix any misheard word inline before exporting. Faster and safer than scrubbing through a recording by hand.", 'tp_interview_transcription_faq2_q': 'Can it separate my questions from their answers?', 'tp_interview_transcription_faq2_a': 'With speaker labels (Pro or a credit pack), yes — two-voice separation is diarization\'s best case, and you can rename the labels to "Q" and "A" in one click each. On the free tiers the transcript runs together, but question marks and your own memory of the conversation make manual splitting quick for a one-hour interview.', 'tp_interview_transcription_faq3_q': 'Do phone-call recordings work?', 'tp_interview_transcription_faq3_a': 'Yes. Call recordings are narrowband (the classic "phone sound") and the model handles them well, though expect a few more errors on the far end of the line than on your side. AMR files from Android call recorders upload directly — no conversion needed.', 'tp_interview_transcription_faq4_q': 'Do I need consent to record an interview?', 'tp_interview_transcription_faq4_a': "Rules vary by place: some jurisdictions require only one party's consent (yours), others require everyone's. Journalism and research ethics codes generally expect disclosure regardless of the legal floor. This isn't legal advice — check your jurisdiction — but the safe universal practice is simple: ask on tape, and keep the ask in the recording.", 'tp_interview_transcription_faq5_q': 'How much does a 90-minute interview cost to transcribe?', 'tp_interview_transcription_faq5_a': 'With a $5 credit pack (600 minutes), a 90-minute interview costs 90 credits — 75 cents, no subscription, and the rest of the pack never expires. A human transcription service charges $90–135 for the same audio. Interviews up to 30 minutes are free with no account; up to an hour with a free account.', 'tp_spanish_title': 'Transcribe Spanish Audio to Text — Free AI | transcribe.free', 'tp_spanish_desc': 'Spanish speech to text, free and no sign-up. Latin American and Castilian Spanish, up to 30 min per file. Edit, then export TXT, SRT, VTT.', 'tp_spanish_h1': 'Transcribe Spanish Audio to Text', 'tp_spanish_sub': 'Español to accurate text — Latin American or Castilian, auto-punctuated with proper accents. Free, no account needed.', 'tp_spanish_sec0_h': 'Dialect coverage: both sides of the Atlantic', 'tp_spanish_sec0_p0': "Spanish is one of the model's strongest languages — second only to English in training coverage. Mexican, Colombian, Rioplatense (Argentina/Uruguay, including voseo), Caribbean, Andean, and Castilian Spanish all transcribe at the model's top accuracy tier. Fast Caribbean speech with dropped syllable-final s is the hardest case; expect a few more fixes there.", 'tp_spanish_sec0_p1': "Distinción vs seseo doesn't matter to the output: the transcript is written in standard orthography either way, with ñ, accent marks, and inverted ¿¡ placed by the model.", 'tp_spanish_sec1_h': 'Spanglish and code-switching', 'tp_spanish_sec1_p0': 'Real conversations flip between Spanish and English mid-sentence. With the language pinned to Spanish (as it is on this page), English fragments are usually transcribed as English words inside Spanish text rather than being mangled — but long English passages come out better if you use the auto-detect transcriber on the home page instead, which switches per file.', 'tp_spanish_faq0_q': 'Does it handle Latin American and Castilian Spanish equally?', 'tp_spanish_faq0_a': 'Yes. The training data skews slightly Latin American by volume, but Castilian (including distinción) transcribes at the same tier. Regional vocabulary — vosotros forms, voseo conjugations, Mexican and Argentine slang — is written as spoken.', 'tp_spanish_faq1_q': 'How accurate is Spanish transcription really?', 'tp_spanish_faq1_a': "Spanish sits in the model's top accuracy tier, typically within a point or two of English on clear audio — near-human for broadcast-quality speech. Accuracy dips on very fast Caribbean speech and heavy crosstalk, which is what the built-in editor is for.", 'tp_spanish_faq2_q': 'Will accents and ñ come out right in the text?', 'tp_spanish_faq2_a': 'Yes. Output is standard Spanish orthography: tildes (á, é, í, ó, ú), ñ, ü, and inverted question/exclamation marks are all produced by the model automatically. You get properly written Spanish, not a stripped ASCII approximation.', 'tp_spanish_faq3_q': 'What about Spanglish — mixed Spanish and English?', 'tp_spanish_faq3_a': 'Short English phrases inside Spanish speech ("okay", brand names, work jargon) are transcribed inline correctly on this page. If your recording is genuinely half-and-half, use the auto-detect uploader on the home page — pinning Spanish forces borderline sentences toward Spanish spellings.', 'tp_spanish_faq4_q': 'Can I transcribe Spanish audio directly into English text?', 'tp_spanish_faq4_a': 'Not on this page — this transcribes Spanish speech into Spanish text, which is the accurate path. Machine-translating the transcript afterwards (with any translator you like) preserves far more meaning than asking a speech model to translate on the fly. Transcript translation is on our roadmap.', 'tp_spanish_faq5_q': 'Is Catalan, Galician, or Basque covered here?', 'tp_spanish_faq5_a': "Not by this page — they're separate languages, not Spanish dialects. The model does support Catalan, Galician, and Basque: upload on the home page with auto-detect, or pin the language in the options there.", 'tp_french_title': 'Transcribe French Audio to Text — Free AI | transcribe.free', 'tp_french_desc': 'French speech to text, free and no sign-up. Metropolitan, Canadian and African French, up to 30 min per file free. Export TXT, SRT, VTT.', 'tp_french_h1': 'Transcribe French Audio to Text', 'tp_french_sub': 'Français to clean, accented text — Metropolitan, Québécois, or African French. Free, no account needed.', 'tp_french_sec0_h': 'Which French? All of them, with one caveat', 'tp_french_sec0_p0': 'Metropolitan French is a top-tier language for the model — accuracy on clear Parisian-register speech approaches English. Belgian and Swiss French (with septante/nonante) transcribe just as well. Canadian French is well covered for formal and broadcast speech; strong joual — informal Québécois with heavy vowel shifts and contractions like "chu" for "je suis" — is the one register where you\'ll notice more errors, usually normalized toward standard spelling.', 'tp_french_sec0_p1': "West and Central African French (Senegal, Côte d'Ivoire, Cameroon, DRC) transcribes reliably in news/formal registers; heavy code-switching with Wolof, Lingala, or Nouchi slang will show more misses.", 'tp_french_sec1_h': 'Orthography the way French should look', 'tp_french_sec1_p0': 'Output uses full French orthography: accents (é, è, ê, à, ç), apostrophes and elisions (l\'homme, j\'ai), and French punctuation conventions. Liaison and silent letters are handled by the language model — you get "les enfants", never a phonetic rendering.', 'tp_french_faq0_q': 'Does Canadian French (Québécois) work?', 'tp_french_faq0_a': 'Yes for most content: newscasts, meetings, lectures, and podcasts in Canadian French transcribe near the Metropolitan tier. Informal joual is the weak spot — heavily contracted speech tends to be normalized to standard French spelling, and dense slang picks up more errors.', 'tp_french_faq1_q': 'What about African French accents?', 'tp_french_faq1_a': 'Well covered in formal registers — Ivorian, Senegalese, Cameroonian, and Congolese French speech transcribes reliably for interviews and broadcasts. Where accuracy drops is rapid code-switching into Wolof, Bambara, Lingala, or Nouchi within the same sentence; those fragments may come out garbled.', 'tp_french_faq2_q': 'How accurate is French compared to English?', 'tp_french_faq2_a': "French is in the model's top tier — on clean audio it's within roughly a point of English word accuracy. Homophone-rich French (est/et/ait, ses/ces/c'est) is disambiguated by context surprisingly well, though that's where remaining errors cluster; a quick editor pass catches them.", 'tp_french_faq3_q': 'Are accents and elisions written correctly?', 'tp_french_faq3_a': "Yes — the transcript is standard French orthography with all diacritics (é è ê ë à â ç ô û ï) and proper elision (d'accord, qu'il, l'équipe). Numbers are usually written as digits; Belgian/Swiss septante and nonante are transcribed as spoken.", 'tp_french_faq4_q': 'Can I get an English transcript from French audio?', 'tp_french_faq4_a': 'This page transcribes French speech into French text — the highest-accuracy path. For an English version, export the French TXT and run it through the translator of your choice; translating accurate text beats direct speech-translation on quality. Built-in transcript translation is planned.', 'tp_french_faq5_q': 'Will it caption my French video for YouTube?', 'tp_french_faq5_a': 'Yes — upload the video file here (MP4/MOV/MKV all work), and export SRT when it\'s done. The cues are split subtitle-length with French punctuation intact, ready for YouTube Studio\'s "Upload file → With timing" flow or for Premiere/Resolve.', 'tp_german_title': 'Transcribe German Audio to Text — Free AI | transcribe.free', 'tp_german_desc': 'German speech to text, free and no sign-up. Standard German strong; Swiss/Austrian dialect caveats explained. Export TXT, SRT, VTT.', 'tp_german_h1': 'Transcribe German Audio to Text', 'tp_german_sub': 'Deutsch to precise text with capitalized nouns, umlauts and ß. Free, no account needed.', 'tp_german_sec0_h': 'Hochdeutsch first, dialects with eyes open', 'tp_german_sec0_p0': 'Standard German (Hochdeutsch) — including regionally colored standard as spoken in Bavaria, northern Germany, or Vienna — is a top-tier language for the model. Compound words come out correctly assembled (Geschwindigkeitsbegrenzung, not three fragments), and noun capitalization follows German rules automatically.', 'tp_japanese_desc': 'Japanese speech to text, free and no sign-up. Kanji/kana output with proper segmentation. Up to 30 min free. Export TXT, SRT, VTT.', 'tp_japanese_h1': 'Transcribe Japanese Audio to Text', 'tp_german_sec0_p1': 'The honest caveat: Swiss German (Schwiizerdütsch) is not Standard German. Alemannic dialect speech is effectively another language to the model — it will either normalize it roughly into High German or produce errors. Swiss speakers reading Standard German, or Swiss broadcast German, transcribe fine; a casual Zürich dinner conversation will not. The same applies, milder, to deep Bavarian and Austrian dialect — Austrian standard German is excellent, broad dialect is not.', 'tp_german_sec1_h': 'German orthography, done properly', 'tp_german_sec1_p0': "Output follows modern German spelling: capitalized nouns, umlauts (ä, ö, ü), ß where the reformed rules put it, and sentence punctuation suited to German's long clause structure. If a speaker uses English tech vocabulary mid-sentence — ubiquitous in German workplaces — those words are transcribed as English inline.", 'tp_german_faq0_q': 'Does Swiss German work?', 'tp_german_faq0_a': 'Honestly: not well. Swiss German dialect (Schwiizerdütsch) differs from Standard German more than Dutch does, and the model treats it as noisy German — output tends to be a rough High-German normalization with real errors. Swiss speakers speaking Standard German transcribe excellently. For dialect recordings, budget editor time.', 'tp_german_faq1_q': 'And Austrian German?', 'tp_german_faq1_a': 'Austrian standard German — media, meetings, lectures — is top-tier, including Austrian vocabulary (Jänner, Erdapfel) written as spoken. Deep rural dialect gets rougher, the same pattern as Bavaria: the further from standard, the more the model normalizes or misses.', 'tp_german_faq2_q': 'Are umlauts, ß and capitalized nouns handled?', 'tp_german_faq2_a': 'Yes — the transcript is proper German orthography: ä/ö/ü, ß vs ss per the reformed rules, and nouns capitalized. You won\'t get "strasse" for "Straße" or lowercase nouns to fix afterwards.', 'tp_german_faq3_q': 'How does it do with long compound words?', 'tp_german_faq3_a': "Well — compounds are where German speech models used to fall apart, and the large model handles them: Donaudampfschifffahrt-style coinages are assembled correctly when clearly spoken. Novel ad-hoc compounds in fast speech are the residual error source; they're quick edits.", 'tp_german_faq4_q': 'Can I turn German audio into English text?', 'tp_german_faq4_a': 'This page produces a German transcript — the accurate path. Export TXT and machine-translate it for an English version; two good steps beat one lossy one. In-app transcript translation is on the roadmap.', 'tp_german_faq5_q': 'Denglisch — German with English mixed in?', 'tp_german_faq5_a': 'Common in tech and business audio, and handled well: English terms ("das Meeting", "gebrieft", product names) are transcribed as English words inside the German sentence. Wholly English passages several sentences long transcribe better via the auto-detect uploader on the home page.', 'tp_portuguese_title': 'Transcribe Portuguese Audio — Free AI | transcribe.free', 'tp_portuguese_desc': 'Portuguese speech to text, free and no sign-up. Brazilian and European Portuguese both covered. Up to 30 min free. Export TXT, SRT, VTT.', 'tp_portuguese_h1': 'Transcribe Portuguese Audio to Text', 'tp_portuguese_sub': 'Português to accurate text — Brazilian or European, with proper accents and punctuation. Free, no account needed.', 'tp_portuguese_sec0_h': 'PT-BR and PT-PT are not the same — both work', 'tp_portuguese_sec0_p0': "Brazilian Portuguese dominates the training data (as it dominates the internet), so PT-BR — from carioca to paulista to northeastern accents — sits in the model's top accuracy tier. European Portuguese transcribes well too, but its vowel reduction (swallowed unstressed vowels) makes it measurably harder than PT-BR; expect slightly more edits for fast Lisbon speech.", 'tp_portuguese_sec0_p1': "Angolan and Mozambican Portuguese pattern close to the European variant and transcribe reliably in formal registers. The transcript follows the speaker's variant: você/tu usage, gerúndio vs a + infinitive, and vocabulary (trem vs comboio) come out as spoken.", 'tp_portuguese_sec1_h': 'Orthography under the Acordo Ortográfico', 'tp_portuguese_sec1_p0': 'Output uses current post-agreement spelling with full diacritics — ã, õ, ç, á, â, é, ê, í, ó, ô, ú — and Portuguese punctuation. Names and English loanwords common in Brazilian business speech are transcribed inline as-is.', 'tp_portuguese_faq0_q': 'Brazilian or European Portuguese — which does this expect?', 'tp_portuguese_faq0_a': "Either — the language is pinned to Portuguese, not to a variant, and the model identifies the variant from the audio itself. PT-BR is the model's stronger side by data volume; PT-PT is solid but its heavy vowel reduction costs a little accuracy on fast informal speech.", 'tp_portuguese_faq1_q': 'How accurate is Portuguese transcription?', 'tp_portuguese_faq1_a': 'Brazilian Portuguese is top-tier — comparable to Spanish, within a couple of points of English on clear audio. European Portuguese runs slightly behind on casual speech because unstressed vowels often disappear entirely; broadcast PT-PT is excellent.', 'tp_portuguese_faq2_q': 'Will accents and ç be written correctly?', 'tp_portuguese_faq2_a': 'Yes. The transcript is standard Portuguese orthography: nasal vowels (ã, õ), cedilla (ç), and acute/circumflex accents all placed by the model. Spelling follows the current Acordo Ortográfico conventions.', 'tp_portuguese_faq3_q': 'Does it handle African Portuguese (Angola, Mozambique)?', 'tp_portuguese_faq3_a': 'Yes, particularly in formal and broadcast registers, where it patterns close to European Portuguese. Informal speech mixing in Kimbundu, Umbundu, or Changana words will transcribe the Portuguese accurately and stumble on the loanwords — quick fixes in the editor.', 'tp_portuguese_faq4_q': 'Can I get English text from Portuguese audio?', 'tp_portuguese_faq4_a': 'This page transcribes Portuguese to Portuguese — the accuracy-preserving path. Export the TXT and run it through a translator for English; translating a clean transcript beats direct speech translation. Built-in translation of transcripts is planned.', 'tp_portuguese_faq5_q': 'Portunhol or Spanish mixed in — what happens?', 'tp_portuguese_faq5_a': 'Border-region speech that drifts between Portuguese and Spanish gets transcribed toward Portuguese spellings on this page, since the language is pinned. For genuinely bilingual recordings, the auto-detect uploader on the home page picks the dominant language per file.', 'tp_japanese_title': 'Transcribe Japanese Audio to Text — Free AI | transcribe.free', 'tp_japanese_sub': '日本語 to properly written text — kanji, kana, and punctuation handled. Free, no account needed.', 'tp_japanese_sec0_h': 'How Japanese comes out: script and segmentation', 'tp_japanese_sec0_p0': "The transcript is written the way Japanese is actually written: a natural mix of kanji, hiragana, and katakana, chosen by context — 会議 not かいぎ, katakana for loanwords and foreign names, kana for grammar. Japanese punctuation (、and 。) is inserted, and since Japanese doesn't use spaces, the text flows unsegmented, exactly as a native writer would produce it.", 'tp_japanese_sec0_p1': "One consequence for subtitles: cue lengths are based on the model's phrase segmentation rather than word counts. The SRT/VTT exports produce short, readable cues, but Japanese subtitle conventions (13–16 characters per line) may mean you split a few cues in the editor for broadcast-style captioning.", 'tp_japanese_sec1_h': 'Registers and dialects', 'tp_japanese_sec1_p0': "Standard Japanese (標準語) — meetings, lectures, podcasts, keigo-heavy business speech — is the model's strong suit and transcribes at a high tier. Kansai-ben and other regional forms are usually rendered correctly or lightly normalized; strong regional dialect from older rural speakers (Tōhoku, Kagoshima) is the genuinely hard case. Homophone-heavy Japanese means the model occasionally picks the wrong kanji for a name — worth a scan in the editor.", 'tp_japanese_faq0_q': 'Does the transcript use kanji or kana?', 'tp_japanese_faq0_a': 'Both, mixed naturally by context — standard written Japanese, not a romaji or all-kana rendering. Common words appear in kanji, grammatical elements in hiragana, loanwords and foreign names in katakana. Rare or ambiguous readings sometimes get the wrong kanji; those are quick edits.', 'tp_japanese_faq1_q': 'How is segmentation handled without spaces?', 'tp_japanese_faq1_a': 'Japanese text is written without spaces and the transcript follows that convention. Segments are split on natural phrase boundaries with 、and 。 punctuation inserted by the model, so the text reads like written Japanese, and SRT cues break at phrase edges rather than mid-word.', 'tp_japanese_faq2_q': 'How accurate is Japanese compared to English?', 'tp_japanese_faq2_a': "High, but a notch below the top European languages — Japanese's pitch accent and massive homophone inventory make kanji selection the main error source rather than mishearing. Clear studio or meeting audio produces very usable transcripts; the editor pass is mostly homophone/kanji checks.", 'tp_japanese_faq3_q': 'Kansai-ben and other dialects?', 'tp_japanese_faq3_a': 'Kansai-ben is common enough in media that the model handles it well, usually writing dialect forms as spoken (あかん, ~へん negatives). Heavier regional dialects — rural Tōhoku, Okinawan-influenced speech — degrade accuracy noticeably. Standard-register speakers with regional accents are no problem.', 'tp_japanese_faq4_q': 'Can I get English text from Japanese audio?', 'tp_japanese_faq4_a': 'This page produces a Japanese transcript, which is the accurate path. For English, export the TXT and machine-translate it — Japanese→English translation quality is much higher on clean text than on direct speech translation. In-app translation is on the roadmap.', 'tp_japanese_faq5_q': 'Will it handle keigo and business Japanese?', 'tp_japanese_faq5_a': 'Yes — polite and honorific registers are heavily represented in training data (news, presentations, service interactions) and transcribe accurately, including humble/honorific verb forms. Casual speech with contractions (っす, じゃん) also comes out as spoken.', 'tp_chinese_title': 'Transcribe Chinese Audio to Text — Free AI | transcribe.free', 'tp_chinese_desc': 'Mandarin speech to text, free and no sign-up. Simplified characters, proper punctuation. Cantonese is separate (yue). Export TXT, SRT, VTT.', 'tp_chinese_h1': 'Transcribe Chinese Audio to Text', 'tp_chinese_sub': '中文 (Mandarin) to written Chinese — simplified characters, clean punctuation. Free, no account needed.', 'tp_chinese_sec0_h': 'Mandarin, and the Cantonese caveat that matters', 'tp_chinese_sec0_p0': 'This page is pinned to Mandarin (zh) — 普通话/国语 as spoken in mainland China, Taiwan, Singapore, and Malaysia. Standard Mandarin transcribes at a high tier, including accented Mandarin from southern speakers.', 'tp_chinese_sec0_p1': "Cantonese is NOT a Mandarin dialect for speech-recognition purposes — it's a separate language with its own code (yue), its own vocabulary, and its own written form. A Cantonese recording pushed through this page will produce garbage-to-mediocre Mandarin text. We deliberately don't index a Cantonese page yet because output quality doesn't meet our bar; for Cantonese audio, expect to look at dedicated Cantonese tooling.", 'tp_chinese_sec1_h': 'Simplified output, punctuation, and mixed speech', 'tp_chinese_sec1_p0': 'Transcripts are produced in simplified characters by default (the dominant training convention) with full-width Chinese punctuation (，。？) inserted — Chinese is written without spaces and the output follows that. Taiwanese Mandarin speakers should note the transcript will typically be simplified, not traditional; converting script is a lossless one-click step in many tools. English words and brand names inside Mandarin speech are transcribed inline in Latin script.', 'tp_chinese_faq0_q': 'Does this work for Cantonese?', 'tp_chinese_faq0_a': "No — and it's important to know why: Cantonese (yue) is a different language from Mandarin (zh), not an accent. This page pins Mandarin. Cantonese audio here will come out badly. The underlying model has some Cantonese ability under its separate yue code, but we don't consider it good enough to ship a page for yet.", 'tp_chinese_faq1_q': 'Simplified or traditional characters in the output?', 'tp_chinese_faq1_a': "Simplified, as a rule — that's the dominant convention in the model's Mandarin training data, even for Taiwanese speakers. If you need traditional characters, run the exported TXT through any simplified→traditional converter; the conversion is essentially lossless in that direction.", 'tp_chinese_faq2_q': 'How accurate is Mandarin transcription?', 'tp_chinese_faq2_a': 'High tier — clear Mandarin (broadcast, meetings, lectures) transcribes very reliably, including tone-dependent disambiguation, because the language model picks characters from context. Strong regional accents (Sichuan-flavored Mandarin, Taiwanese-accented Mandarin) still work; actual regional languages (Shanghainese, Hokkien) do not.', 'tp_chinese_faq3_q': 'How does punctuation and spacing work in the transcript?', 'tp_chinese_faq3_a': 'Chinese is written without spaces, and the transcript follows suit, with full-width punctuation (，。！？、) inserted at natural boundaries. Segment/SRT cue splits land on phrase boundaries, so subtitles read naturally rather than breaking mid-word.', 'tp_chinese_faq4_q': 'Mandarin audio to English text — possible?', 'tp_chinese_faq4_a': "This page transcribes Mandarin into Chinese text; that's the high-accuracy step. For English, export TXT and machine-translate — zh→en translation on clean text is strong, and the two-step result beats one-shot speech translation. Built-in transcript translation is planned.", 'tp_chinese_faq5_q': 'What about English words mixed into Mandarin speech?', 'tp_chinese_faq5_a': 'Very common in tech and business Mandarin, and handled well: English terms, acronyms, and brand names are transcribed inline in Latin script (e.g. 我们用 Kubernetes 部署). Long English-only passages transcribe better via the auto-detect uploader on the home page.', 'tp_arabic_title': 'Transcribe Arabic Audio to Text — Free AI | transcribe.free', 'tp_arabic_desc': 'Arabic speech to text, free and no sign-up. MSA strong; dialect caveats explained honestly. Right-to-left output. Export TXT, SRT, VTT.', 'tp_arabic_h1': 'Transcribe Arabic Audio to Text', 'tp_arabic_sub': 'العربية to text — Modern Standard Arabic at high accuracy, major dialects with honest caveats. Free, no account needed.', 'tp_arabic_sec0_h': 'MSA is the strong case; dialects vary', 'tp_arabic_sec0_p0': "Modern Standard Arabic (فصحى) — news, speeches, lectures, formal interviews — transcribes at a high tier. That's where the training data is richest and where you can expect near-European-language accuracy on clear audio.", 'tp_arabic_sec0_p1': 'Spoken Arabic is diglossic, and the dialects are where honesty matters: Egyptian and Levantine (the media-heavy dialects) transcribe reasonably well, often lightly normalized toward MSA spellings. Gulf dialects are serviceable. Maghrebi (Moroccan/Algerian darija) is the hard case — heavy French/Berber mixing and phonology far from MSA mean noticeably rougher output. For darija recordings, budget real editor time.', 'tp_arabic_sec1_h': 'Right-to-left text, hamza, and taa marbuta', 'tp_arabic_sec1_p0': 'Output is proper right-to-left Arabic script with standard orthography — hamza seats, taa marbuta, and alif variants written conventionally. Short vowels (harakat) are not written, as in normal Arabic text. The editor and all exports handle RTL correctly, and SRT/VTT files carry the Arabic text ready for players that support RTL subtitles (most modern ones do).', 'tp_arabic_faq0_q': 'Which Arabic does this handle best?', 'tp_arabic_faq0_a': "Modern Standard Arabic, clearly — newscasts, speeches, and formal registers transcribe at the model's high tier. Among dialects: Egyptian and Levantine best (media exposure), Gulf next, Maghrebi darija weakest. Mixed MSA/dialect speech, common in interviews, comes out mostly right with dialect words sometimes normalized.", 'tp_arabic_faq1_q': 'Will Moroccan/Algerian darija work?', 'tp_arabic_faq1_a': "Set expectations low: darija's French and Amazigh mixing, plus phonology far from MSA, make it the hardest mainstream Arabic variant. You'll get a usable skeleton for clear speech but should plan on editing. For formal Maghrebi speech (news, education), accuracy is much better.", 'tp_arabic_faq2_q': 'Does the transcript include harakat (short vowels)?', 'tp_arabic_faq2_a': "No — like virtually all written Arabic, the output is unvocalized: consonants and long vowels only, with hamza and taa marbuta written correctly. That's the standard for readable Arabic text; fully vocalized output isn't something speech models produce reliably.", 'tp_arabic_faq3_q': 'Is right-to-left handled properly in exports?', 'tp_arabic_faq3_a': 'Yes. The editor renders RTL naturally, TXT exports are plain UTF-8 Arabic text, and SRT/VTT subtitle files work in players with RTL support (YouTube, VLC, modern web players). Mixed-direction lines — Arabic with an English brand name — follow standard bidi rendering.', 'tp_arabic_faq4_q': 'Arabic audio to English text?', 'tp_arabic_faq4_a': 'This page transcribes Arabic into Arabic — the accurate step. For English, export the TXT and machine-translate it; ar→en translation on clean text is far ahead of one-shot speech translation, especially for MSA. Transcript translation inside the app is on the roadmap.', 'tp_arabic_faq5_q': 'Quran recitation or religious audio?', 'tp_arabic_faq5_a': "Tajwid recitation is sung/melodic and highly stylized — the model often recognizes the text (much of it is in training data) but this isn't a reliable Quran transcription tool, and output won't carry correct vocalization. For khutbas, lectures, and du'a in spoken register, it performs like normal MSA/dialect speech.", 'tp_hindi_title': 'Transcribe Hindi Audio to Text — Free AI | transcribe.free', 'tp_hindi_desc': 'Hindi speech to text, free and no sign-up. Devanagari output, Hinglish code-switching handled. Up to 30 min free. Export TXT, SRT, VTT.', 'tp_hindi_h1': 'Transcribe Hindi Audio to Text', 'tp_hindi_sub': 'हिन्दी to Devanagari text — Hinglish code-switching included. Free, no account needed.', 'tp_hindi_sec0_h': 'Devanagari out, Hinglish in', 'tp_hindi_sec0_p0': 'Transcripts are written in Devanagari script (हिन्दी), with Hindi punctuation and sentence structure. Real Indian speech, though, is rarely pure Hindi — Hinglish code-switching is the norm, and the model handles it the way Hindi media does: English words and phrases inside Hindi sentences are usually transcribed in Latin script inline (आज हम discuss करेंगे next quarter के targets), matching how Hinglish is actually written.', 'tp_hindi_sec0_p1': 'Predominantly English speech with Hindi phrases mixed in works better through the auto-detect uploader on the home page, which will treat it as English.', 'tp_hindi_sec1_h': 'Accuracy tier and the Urdu question', 'tp_hindi_sec1_p0': "Hindi sits in the model's solid mid-high tier: clear speech — YouTube content, lectures, interviews — produces very usable transcripts, a step below the top European languages mostly due to code-switching density and speaker variety. Spoken Hindi and Urdu overlap heavily; on this page the output is Devanagari, so Urdu-register speech will be written in Devanagari, not Nastaliq. For Urdu-script output, that's a separate language code (ur) via the home page.", 'tp_hindi_faq0_q': 'Is the output in Devanagari or Latin letters?', 'tp_hindi_faq0_a': "Devanagari for the Hindi, Latin for embedded English — the way written Hinglish actually looks. You won't get an all-romanized transcript. If you need romanized Hindi, transliterate the exported TXT with any Devanagari→Latin tool afterwards.", 'tp_hindi_faq1_q': 'How well does Hinglish code-switching work?', 'tp_hindi_faq1_a': 'Well — it\'s the defining feature of modern Hindi audio and the training data reflects that. Mid-sentence English ("basically", "presentation", full clauses) is transcribed inline in Latin script. Where it wobbles is rapid-fire switching every few words; expect the occasional wrong-script rendering to fix in the editor.', 'tp_hindi_faq2_q': 'How accurate is Hindi transcription overall?', 'tp_hindi_faq2_a': 'Solidly usable: on clear audio (podcasts, lectures, broadcast) you get a transcript that needs light editing, a tier below English/Spanish. Regional accents from non-native Hindi speakers and heavy background noise pull accuracy down faster than they do for English.', 'tp_hindi_faq3_q': 'What about Urdu — same spoken language, different script?', 'tp_hindi_faq3_a': 'Spoken Hindustani is largely shared, and the model will transcribe Urdu-register speech here — but in Devanagari, since this page pins Hindi. For Urdu output in Nastaliq/Arabic script, upload via the home page and pin Urdu (ur) in the options instead.', 'tp_hindi_faq4_q': 'Hindi audio to English text?', 'tp_hindi_faq4_a': 'This page produces the Hindi transcript — the accurate step. Export TXT and machine-translate for English; hi→en translation on clean text is strong. One-shot speech translation loses more, especially on code-switched content. In-app translation is planned.', 'tp_hindi_faq5_q': 'Do Bollywood songs or bhajans transcribe?', 'tp_hindi_faq5_a': 'Speech is the design target; singing is best-effort. Clear solo vocals often come out mostly right, but film songs with full orchestration will be patchy. Dialogue scenes, interviews, and vlogs transcribe like normal speech.', 'tp_korean_title': 'Transcribe Korean Audio to Text — Free AI | transcribe.free', 'tp_korean_desc': 'Korean speech to text, free and no sign-up. Hangul output with correct spacing and particles. Up to 30 min free. Export TXT, SRT, VTT.', 'tp_korean_h1': 'Transcribe Korean Audio to Text', 'tp_korean_sub': '한국어 to Hangul text with correct spacing and particles. Free, no account needed.', 'tp_korean_sec0_h': 'Hangul output, spacing, and particles', 'tp_korean_sec0_p0': 'Korean writes with spaces, but the rules (띄어쓰기) are notoriously fiddly — particles attach to their noun, compound verbs split or join by convention. The transcript applies standard spacing automatically, attaches particles (은/는/이/가/을/를) correctly, and inserts sentence punctuation. Output is pure Hangul with Latin script for embedded English; hanja are not used, matching modern written Korean.', 'tp_korean_sec0_p1': 'Honorific register (합쇼체, 해요체) and casual speech (반말) are transcribed as spoken — verb endings come out the way the speaker said them, which matters for interviews and variety-show content.', 'tp_korean_sec1_h': 'What transcribes well, and what to watch', 'tp_korean_sec1_p0': "Seoul-standard Korean — podcasts, lectures, meetings, YouTube — sits in the model's high tier. Fast variety-show banter with overlapping speakers and sound effects is the classic hard case (as it is for human transcribers). Satoori (regional dialects): Gyeongsang and Jeolla accents on standard vocabulary transcribe fine; deep Jeju dialect is effectively out of scope. Konglish loanwords (아이스아메리카노, 미팅) are written in Hangul as Koreans write them.", 'tp_korean_faq0_q': 'Does the transcript follow Korean spacing rules?', 'tp_korean_faq0_a': "Yes — 띄어쓰기 is applied by the language model to standard conventions: particles bound to their nouns, dependent nouns spaced, common compounds joined. It's the same standard a careful Korean writer would use, and far more consistent than raw speech models used to be.", 'tp_korean_faq1_q': 'Are particles and verb endings accurate?', 'tp_korean_faq1_a': 'Particles are a strong point — 이/가 vs 은/는 and object marking come out correctly from context. Verb endings are transcribed as spoken, preserving register: 합니다 stays 합니다, 반말 stays 반말. Contracted casual forms (뭐해 for 무엇을 해) are written the colloquial way.', 'tp_korean_faq2_q': 'How accurate is Korean overall?', 'tp_korean_faq2_a': "High tier on clear speech — Korean is one of the model's better-covered Asian languages thanks to abundant media data. The gap to English shows up on fast overlapping conversation and slang-dense speech; single-speaker content (lectures, vlogs) is excellent.", 'tp_korean_faq3_q': 'What about satoori (regional dialects)?', 'tp_korean_faq3_a': "Gyeongsang, Jeolla, and Chungcheong accents speaking near-standard Korean transcribe well — intonation differences don't hurt much. Heavy dialect vocabulary gets normalized or missed, and Jeju dialect (effectively a separate language) is out of scope.", 'tp_korean_faq4_q': 'Korean audio to English text?', 'tp_korean_faq4_a': 'This page produces the Korean transcript; for English, export TXT and machine-translate. ko→en translation on clean text is strong, and the two-step route preserves more nuance (especially register) than one-shot speech translation. In-app translation is on the roadmap.', 'tp_korean_faq5_q': 'Will it handle K-content — variety shows, K-pop, dramas?', 'tp_korean_faq5_a': "Dramas and interviews: yes, that's normal speech. Variety shows: expect more errors — overlapping shouting, sound effects, and on-screen text culture make them hard even for humans. K-pop songs: singing is best-effort; clear ballad vocals do better than dense rap sections.", 'tp_italian_title': 'Transcribe Italian Audio to Text — Free AI | transcribe.free', 'tp_italian_desc': 'Italian speech to text, free and no sign-up. Standard Italian and regional accents, up to 30 min per file free. Export TXT, SRT, VTT.', 'tp_italian_h1': 'Transcribe Italian Audio to Text', 'tp_italian_sub': 'Italiano to clean text with proper accents and apostrophes. Free, no account needed.', 'tp_italian_sec0_h': 'Standard Italian and its regional colors', 'tp_italian_sec0_p0': "Standard Italian — the register of RAI, podcasts, lectures, and meetings — transcribes at the model's top tier. Regional accents (Milanese, Roman, Neapolitan, Sicilian speakers speaking Italian) are no obstacle: accent coloring, gemination differences, and regional intonation are absorbed without hurting accuracy. Swiss Italian (Ticino) patterns the same.", 'tp_italian_sec0_p1': 'The distinction that matters is accent vs language: actual dialetti — Neapolitan, Sicilian, Venetian as languages — are not Italian, and pushing a true dialect recording through this page will produce a rough Italianization. Italian speech peppered with dialect words comes out fine, with the dialect terms usually written as spoken.', 'tp_italian_sec1_h': 'Orthography and the editor pass', 'tp_italian_sec1_p0': "Output is standard Italian orthography: grave/acute accents where they belong (è, perché, città), apostrophized elisions (l'anno, un'ora, po'), and Italian punctuation. Typical residual errors cluster on proper names and fast interruption-heavy conversation (a national sport); both are quick fixes in the editor before export.", 'tp_italian_faq0_q': 'Do regional accents affect accuracy?', 'tp_italian_faq0_a': 'Barely, for accents on standard Italian — a Sicilian or Milanese accent speaking Italian transcribes at the same tier as a RAI announcer. What degrades output is switching into true dialetto (Neapolitan, Venetian, Sicilian as languages), which the model can only approximate as Italian.', 'tp_italian_faq1_q': 'How accurate is Italian transcription?', 'tp_italian_faq1_a': "Top tier — comparable to Spanish and French, close behind English on clean audio. Italian's transparent orthography helps: what's heard maps predictably to spelling. Remaining errors concentrate on names, numbers spoken quickly, and everyone-talking-at-once dinner-table audio.", 'tp_italian_faq2_q': 'Are accents and apostrophes written correctly?', 'tp_italian_faq2_a': "Yes — è vs é, perché, più, città, and elisions like l'ho detto or un'idea are produced correctly by the model. You get properly written Italian, ready to paste into a document without an accent-fixing pass.", 'tp_italian_faq3_q': 'Can it handle Swiss Italian?', 'tp_italian_faq3_a': 'Yes — Ticinese Italian is standard Italian with regional flavor and transcribes normally, including Swiss vocabulary (natel for cellulare) written as spoken. German or French loans in Swiss-Italian workplace speech are transcribed inline.', 'tp_italian_faq4_q': 'Italian audio to English text?', 'tp_italian_faq4_a': 'This page transcribes Italian to Italian — the accurate step. Export the TXT and machine-translate for English; it→en on clean text is excellent, and the two-step path beats direct speech translation. Built-in transcript translation is planned.', 'tp_italian_faq5_q': 'Will it transcribe fast, overlapping Italian conversation?', 'tp_italian_faq5_a': "It handles fast Italian well — pace alone isn't a problem. Overlap is: when two people genuinely talk over each other, whichever voice dominates gets transcribed and the other drops. For interviews and podcasts this is rarely an issue; for heated roundtables, expect gaps at the pile-ups.", 'tp_podcast_transcription_sec0_h': "Why podcasters transcribe (it isn't just accessibility)", 'tp_voice_memo_transcription_faq1_q': 'Can I record directly on this page instead of uploading?', 'podcast_transcription': 'Podcast Transcription', 'voice_memo_transcription': 'Voice Memo to Text', 'rec_or': 'or record right here', 'rec_start': 'Record', 'rec_stop': 'Stop', 'rec_transcribe': 'Transcribe recording', 'rec_discard': 'Discard', 'rec_mic_denied': "Microphone access was blocked — allow it in your browser's site settings, or upload a file instead.", 'sample_heading': 'What the output looks like', 'tp_podcast_transcription_title': 'Podcast Transcription — Free AI, Show Notes & Captions | transcribe.free', 'tp_podcast_transcription_desc': 'Transcribe podcast episodes free. Show notes, quotes, captions for video podcasts, searchable back catalog — no sign-up. $5 covers 10 hours of back-catalog audio.', 'tp_podcast_transcription_h1': 'Podcast Transcription', 'tp_podcast_transcription_sub': 'Episodes into show notes, quotes, and captions. Free for shorter episodes, and a whole back catalog for the price of a coffee.', 'tp_podcast_transcription_sec0_p0': "A transcript is the only version of your episode Google can read. Publishing one under each episode gives search engines an hour of indexable text per show — listeners find you by searching a phrase a guest said, not just your title. The same text is your show-notes draft: skim the transcript, pull the three best quotes for social posts, lift the topic list for chapter markers, and you've done in ten minutes what used to take a re-listen.", 'tp_podcast_transcription_sec0_p1': "It's also the accessible version of your show for deaf and hard-of-hearing audiences — and if you publish a video version, the SRT export drops straight onto YouTube as captions.", 'tp_podcast_transcription_sec1_h': 'Episode economics: what fits which tier', 'tp_podcast_transcription_sec1_p0': 'A short-form episode (under 30 minutes) transcribes free with no account, three a day. Typical 45–60 minute episodes fit the free account tier. For a back catalog, credit packs are the tool: $5 buys 600 minutes — roughly a season of weekly hour-long episodes — and packs never expire, so you can work through the archive at your own pace. A weekly show that transcribes every new episode plus occasional archive digs is the classic Pro ($10/month) use case.', 'tp_podcast_transcription_sec1_p1': 'Remote interviews recorded as separate tracks (double-enders) transcribe best as the mixed-down episode file — upload the final edit, not the raw stems, so crosstalk cleanup and level differences are already handled.', 'tp_podcast_transcription_faq0_q': "Do transcripts actually help a podcast's SEO?", 'tp_podcast_transcription_faq0_a': "Yes, measurably. Audio is invisible to search engines; a transcript page gives each episode thousands of indexable words in your niche's exact vocabulary. Shows that publish transcripts rank for long-tail phrases spoken mid-episode — queries nobody thinks to put in a title. Export TXT, tidy the filler in the editor first, and paste it under your episode page or into your CMS.", 'tp_podcast_transcription_faq1_q': "What's the fastest show-notes workflow?", 'tp_podcast_transcription_faq1_a': "Transcribe the final mix, then work inside the editor: search for the moments you remember, click their timestamps to confirm the audio, and copy the best lines for pull-quotes. The segment timestamps double as chapter markers — note the times of topic changes as you skim. Ten minutes per episode is realistic once you've done it twice.", 'tp_podcast_transcription_faq2_q': 'My podcast is also on YouTube — can I get captions?', 'tp_podcast_transcription_faq2_a': 'Yes — export SRT and upload it in YouTube Studio (Subtitles → Add → Upload file, "With timing"). Auto-captions on YouTube are worse than a Whisper-class transcript you\'ve spot-checked, and uploading your own SRT means the captions match the polished transcript on your website word for word.', 'tp_podcast_transcription_faq3_q': 'Should I upload the raw double-ender tracks or the final mix?', 'tp_podcast_transcription_faq3_a': "The final mix. Separate host/guest stems mean two uploads, two transcripts, and manual interleaving; the mixed episode gives one transcript in listening order, with music beds and edits already where they'll be for the audience. If you need who-said-what labels, Pro's speaker diarization tags the mixed file per voice.", 'tp_podcast_transcription_faq4_q': 'How do I work through a 100-episode back catalog?', 'tp_podcast_transcription_faq4_a': "A credit pack and a rhythm. $15 buys 2,400 minutes — about 40 hour-long episodes — and $39 buys 9,000 (150 hours); packs never expire, so there's no deadline pressure. Batch by season, transcribe a handful of episodes per sitting, and publish transcripts as you go; each one starts earning search traffic immediately.", 'tp_podcast_transcription_faq5_q': 'Do ads, intro music, and sound effects break the transcript?', 'tp_podcast_transcription_faq5_a': "No — music without speech simply produces no text, so your intro theme becomes a clean gap between segments. Host-read ads transcribe like any other speech (delete them in the editor if you don't want them in show notes). The only trouble spots are speech deliberately buried under loud music, which may need a manual pass.", 'tp_voice_memo_transcription_title': 'Voice Memo to Text — Transcribe or Record in Browser | transcribe.free', 'tp_voice_memo_transcription_desc': 'Turn iPhone and Android voice memos into text free — or record directly in the browser and transcribe in one step. No app, no sign-up, memos auto-delete in 24h.', 'tp_voice_memo_transcription_h1': 'Voice Memo to Text', 'tp_voice_memo_transcription_sub': 'Upload a memo from your phone — or hit record right here and speak. Either way you get clean, editable text in about a minute.', 'tp_voice_memo_transcription_sec0_h': 'Getting a memo off your phone (the annoying part)', 'tp_voice_memo_transcription_sec0_p0': 'iPhone: open Voice Memos, tap the memo, tap the ••• (or share) button → Share, and either AirDrop it to your computer, save it to Files, or share it straight to this page from Safari — it arrives as an M4A that uploads here as-is. Android: most recorder apps (Samsung Voice Recorder, Google Recorder, Easy Voice Recorder) have a share or export action producing M4A, MP3, or 3GP — all supported. WhatsApp and Telegram voice notes export as OGG/Opus, which also upload directly, no conversion.', 'tp_voice_memo_transcription_sec0_p1': "Or skip the file dance entirely: the record button on this page uses your device's microphone and transcribes what you say in one step — handy for capturing a thought on a laptop that has no voice memo app at all.", 'tp_voice_memo_transcription_sec1_h': 'What memos are actually like — and what that means for accuracy', 'tp_voice_memo_transcription_sec1_p0': "Voice memos are the most forgiving thing you can transcribe: one voice, close to the microphone, no crosstalk. A memo recorded normally — phone in hand or on the desk — comes out near-perfect. The classic failure modes are pocket recordings (muffled through fabric) and memos taken while walking on a windy street; both still transcribe, just with more edits needed. Memos fit the free tier by design: almost all are under 30 minutes, so you'll rarely need an account at all.", 'tp_voice_memo_transcription_sec1_p1': "From there it's one click to TXT for your notes app, or copy the text straight from the editor into an email, task manager, or document.", 'tp_voice_memo_transcription_faq0_q': 'How do I get a voice memo off my iPhone?', 'tp_voice_memo_transcription_faq0_a': 'Open Voice Memos, tap the memo, tap the share icon. AirDrop to a Mac, "Save to Files" then upload from iCloud Drive, or — simplest — open this page in Safari on the phone itself, tap the dropzone, and pick the memo from Files. iPhone memos are M4A files and upload without any conversion.', 'tp_voice_memo_transcription_faq2_q': 'Do WhatsApp and Telegram voice notes work?', 'tp_voice_memo_transcription_faq2_a': 'Yes. Export/forward the voice note to yourself and save the file — WhatsApp produces .opus/.ogg, Telegram .ogg — and both upload here directly. Quality is narrowband but single-voice, which the model handles well; expect near-clean text from a normal voice note.', 'tp_voice_memo_transcription_faq3_q': 'My memo is muffled (recorded in a pocket/bag). Any hope?', 'tp_voice_memo_transcription_faq3_a': "Usually, yes — muffled single-voice audio still transcribes, with more errors on names and quiet passages. Upload it as-is: the model was trained on plenty of terrible real-world audio, and fixing a dozen words in the editor beats re-dictating the whole memo. What it can't rescue is speech completely masked by wind or rustling.", 'tp_voice_memo_transcription_faq4_q': "What's the best way to get memos into my notes app?", 'tp_voice_memo_transcription_faq4_a': 'Use "Copy all" in the editor — it puts the clean text on your clipboard for pasting into Notes, Notion, Obsidian, or an email. For archiving, export TXT (the filename matches your memo\'s name). Memos transcribed without an account auto-delete in 24 hours, so copy or export the same day.', 'tp_voice_memo_transcription_faq5_q': 'Can I fix the transcript on my phone before sharing it?', 'tp_voice_memo_transcription_faq5_a': "Yes — the transcript editor works on mobile: tap any line to correct it and it autosaves, then use Copy all or the TXT export from the same screen. For a 2-minute memo that's usually a 30-second cleanup, faster than retyping the memo would have been.", 'tp_spanish_accuracy': 'Top accuracy tier: on clear audio, Spanish transcribes within roughly 1–2 points of English word accuracy.', 'tp_french_accuracy': 'Top accuracy tier: on clear audio, French transcribes within roughly 1–2 points of English word accuracy.', 'tp_german_accuracy': 'Top accuracy tier: on clear audio, German transcribes within roughly 1–2 points of English word accuracy.', 'tp_portuguese_accuracy': 'Top accuracy tier: on clear audio, Portuguese (especially Brazilian) transcribes within roughly 1–2 points of English word accuracy.', 'tp_japanese_accuracy': 'High accuracy tier: clear standard Japanese comes out clean; expect a few more edits on fast overlapping banter or heavy dialect.', 'tp_chinese_accuracy': 'High accuracy tier: clear Mandarin comes out clean; expect more edits on strong regional accents or Cantonese-influenced speech.', 'tp_arabic_accuracy': 'High accuracy tier for Modern Standard Arabic and formal speech; dialect-heavy audio varies, with Egyptian and Levantine strongest.', 'tp_hindi_accuracy': 'Solid mid-high tier: clear Hindi produces a usable transcript that needs light editing — a tier below English or Spanish.', 'tp_korean_accuracy': 'High accuracy tier: clear Korean comes out clean with proper spacing; expect more edits on fast variety-show style overlapping speech.', 'tp_italian_accuracy': 'Top accuracy tier: on clear audio, Italian transcribes within roughly 1–2 points of English word accuracy.', 'home_h1_prefix': 'Free audio & video to text,', 'mode_upload': 'Upload a file', 'mode_record': 'Record audio', 'rec_hint': 'Recording stays on your device until you press Transcribe.', 'tp_home_sub': 'Drop a file or hit record — get an editable transcript in minutes, then export TXT, SRT, or VTT.', 'live_transcription': 'Live Transcription', 'live_draft': 'Live draft', 'copy_label': 'Copy', 'tp_live_transcription_title': 'Live Transcription — Speak & See Text Instantly, Free | transcribe.free', 'tp_live_transcription_desc': 'Free live transcription: your speech streams to our Whisper AI as you talk and text appears seconds later. No app, no sign-up — works in every modern browser.', 'tp_live_transcription_h1': 'Live Transcription', 'tp_live_transcription_sub': 'Press record and your words stream straight to our AI — text appears seconds behind your voice, and a polished transcript lands when you stop.', 'tp_live_transcription_sec0_h': 'Actually live: your speech pipes to our own AI while you talk', 'tp_live_transcription_sec0_p1': 'Because it only needs microphone recording, live mode works in every modern browser — Chrome, Edge, Safari, and Firefox, desktop and phone. Each audio segment is deleted from our servers the moment its text comes back.', 'tp_live_transcription_sec1_h': 'The live feed vs the final transcript', 'tp_live_transcription_sec1_p0': "Segment-by-segment transcription has one built-in limit: the model sees a few seconds at a time, so a word that straddles two segments can come out clipped, and punctuation across segment boundaries is guesswork. That's why the flow ends with one more step: the full recording is kept in your browser while you speak, and pressing Transcribe runs it through the model as a single take — full context, proper punctuation, timestamps, the editor, and TXT/SRT/VTT exports.", 'tp_live_transcription_sec1_p1': "Use the live feed to confirm it's keeping up and to grab text the moment it's spoken (there's a copy button on the feed); use the final pass for anything you'll keep. For audio you already have as a file, upload mode on any tool page is the shorter path.", 'tp_live_transcription_faq0_q': 'Is this actually live, or recorded and sent afterwards?', 'tp_live_transcription_faq0_a': "Actually live: recording and transcription overlap. The page ships each few-second slice of audio to our GPUs while you're still speaking the next one, so text accumulates during the recording, not after it. Expect the feed to run a handful of seconds behind your voice — the time it takes a slice to finish, upload, and transcribe.", 'tp_live_transcription_faq1_q': 'Why is the live text a few seconds behind me?', 'tp_live_transcription_faq1_a': 'Three small delays stack up: a slice has to finish being recorded (three seconds or so), travel to the server, and pass through the model. That usually puts the feed about 4-8 seconds behind your voice — and if our GPUs are briefly busy, the page adapts by sending slightly longer slices instead of falling behind. Dictation-style speech with natural pauses feels smooth.', 'tp_live_transcription_faq2_q': 'Which browsers does live mode work in?', 'tp_live_transcription_faq2_a': 'All modern ones — Chrome, Edge, Safari, and Firefox, on desktop and phones. It relies on standard microphone recording rather than a browser speech service, which is also why Firefox works here even though it lacks built-in dictation.', 'tp_live_transcription_faq3_q': 'Where does my voice go while live transcription runs?', 'tp_live_transcription_faq3_a': "To our servers only, and honestly described: live mode streams your audio to us in short segments as you speak — that's what makes it live — and each segment is deleted immediately after its text comes back. Nothing goes to Google, Apple, or any third-party speech service. The full recording stays in your browser until you press Transcribe, and anonymous transcripts auto-delete within 24 hours.", 'tp_live_transcription_faq4_q': 'Can I use it to follow a meeting or lecture in the room?', 'tp_live_transcription_faq4_a': "As a personal aid, yes — put the device near the speaker and the feed tracks clear speech well, about ten seconds behind. Know the limits: one microphone, so distant voices and crosstalk degrade it, and it isn't a certified captioning service for accessibility compliance. Press Transcribe at the end and the full-context pass usually recovers what the live feed fumbled.", 'tp_live_transcription_faq5_q': 'Which languages work live, and should I pick one?', 'tp_live_transcription_faq5_a': "The same 90+ languages as every transcription on this site — it's the same model. One tip specific to live mode: pick your language in the selector instead of leaving auto-detect on. Detection runs per segment, and seven seconds isn't much evidence, so pinning the language keeps the feed from wavering on short or accented phrases.", 'rec_hint_live': 'Words appear as you speak, transcribed live by our own AI — press Transcribe when you finish for the polished, editable version.', 'tp_voice_memo_transcription_faq1_a': 'Yes — switch to Record audio, allow microphone access, and speak; your words appear as you talk, transcribed live by the same AI that handles uploads. Tap stop to review the clip, then press transcribe for the polished full version. Works in every modern browser, on desktop and phones.', 'tp_live_transcription_sec0_p0': 'While you record, the page slices the microphone stream into short segments — a few seconds each, cut adaptively so the next one ships the moment the previous one comes back — and pipes each straight to our GPU servers, where the same Whisper-class model that powers the whole site transcribes it immediately. The text lands in the live feed seconds behind your voice and keeps flowing for as long as you keep talking. No browser speech service, no third-party dictation API — the live text is real Whisper output from our own hardware.', 'cancelled_instantly': 'Cancellation takes effect instantly', 'credits_dont_expire': 'Any credits you have purchased stay on your account — credits never expire.', 'account_deleted': 'Account deleted', 'account_has_been_deleted': 'Your account has been deleted.', 'delete_account_info': 'Deleting your account is permanent. Your transcripts, remaining credits, and subscription will be removed.', 'checkout': 'Checkout', 'total': 'Total', 'month': 'month', 'purchase': 'Purchase', 'card_number': 'Card number', 'expiration_date': 'Expiration date', 'enter_code_emailed': 'Enter this code on the verification page to confirm your email', 'team': 'Team', 'payment_recieved': 'Payment received', 'payment_id': 'Payment ID', 'plan': 'Plan', 'restore_password_email': 'We received a request to reset your password. Open the link below to choose a new one. If you did not request this, you can ignore this email.'}
Credit is optional - CC0 requires none.
