Start transcribing
Sign up now to start transcribing your audio and video files with high accuracy, secure and private processing, and industry-leading features like speaker diarization and subtitle generation.
Upload a video and read what was said. Videos up to 10 minutes are free without an account; with a free account you get 30 free minutes, speaker labels and faster processing, and after that you pay per minute – no subscription. MP4 is what most people bring here: 42 % of all uploads, ahead of every audio format.
Any common video format: MP4, MOV, WebM, MPEG and 3GP – the audio track is extracted for you, nothing to convert.
Transcript or subtitles: download plain text, or SRT and VTT with timestamps to caption the video.
Speaker labels: with a free account, interviews and meetings come back with each speaker marked.
Language detected automatically: 55 languages have been detected on this site so far – English, Spanish, French, Portuguese, German, Arabic and more.
Private by default: uploads are deleted after 30 days; delete a transcript and its file earlier yourself.
Free up to 10 minutes without an account · 30 free minutes with one.
Supported formats: MP4, MOV, WebM, MPEG, 3GP · Prices
Almost half of everything transcribed here is video; MP4 alone is 42 % of uploads. Most are short – the typical MP4 is under two minutes – and long ones are billed by the minute.
Facts updated August 2026
On OpenAI’s published benchmark of read speech (Common Voice 15) the large-v3 model makes about one error in 11 words in English, one in 21 in Spanish, one in 18 in German, one in 17 in Portuguese and Russian, one in 9 in French. On clean studio recordings (FLEURS) it is roughly a third better. Independent testing on real meetings and calls (Open ASR Leaderboard, 2026) puts English at 7–11 % word error. transcribe.mov runs the faster “turbo” build of the same model, which is a few tenths of a point behind on English. Real files are harder than benchmarks: background noise, cross-talk and strong accents add errors, and a wrong language guess ruins a transcript.
Sources: OpenAI large-v3 release chart (Common Voice 15, FLEURS), Open ASR Leaderboard paper 2026-03-30.
A video file is a container: MP4 (and MOV, its QuickTime relative) wraps a video stream – H.264 or HEVC – and an audio stream, usually AAC. Transcription only needs the audio, so the resolution and the codec of the picture do not matter and you never have to convert the file first. A 4K clip and a 480p clip of the same talk give the same transcript.
Phones record MP4 (Android) or MOV (iPhone), meeting tools export MP4, screen recorders write MP4, MOV or WebM, and video editors export MP4 by default. WebM is what browser-based recorders produce. All of these are accepted up to 50 MB as a guest and up to 4 GB with an account – a two-hour 1080p recording is typically 2–4 GB.
Plain text, split where the model heard pauses; SRT and VTT subtitle files with cues of a few seconds each; JSON with every word and its timing; and TSV for spreadsheets. Most people download the text; about one in three of the subtitle users here comes back for more than one file.
Three cues from a transcribed video, exactly as the SRT download is written: a number, the start and end time to the millisecond, the text. Players and editors read this format directly.
1 00:00:00,000 --> 00:00:03,240 Welcome back. Today we're looking at the quarterly numbers. 2 00:00:03,600 --> 00:00:07,180 Revenue is up eight percent, mostly from returning customers. 3 00:00:07,520 --> 00:00:10,900 Let's start with what changed since the last update.
VTT is the same content with a WEBVTT header and dots instead of commas in the timestamps – the format browsers and YouTube expect.
MP4, MOV (QuickTime), WebM, MPEG and 3GP. The audio track is extracted automatically; there is nothing to convert. If a format is not accepted, export the clip as MP4 from your phone or editor – that always works.
Up to 10 minutes and 50 MB without an account, free. A free account gives you 30 free minutes and files up to 2 hours and 4 GB. Beyond that you buy minutes: 120 for $5.90, 300 for $10.90, 600 for $19.90 – about $2–3 per hour of video, one-time, no subscription, and the minutes never expire.
Yes. Every transcript can be downloaded as SRT or VTT with timestamps. Both are accepted by Premiere, Final Cut, DaVinci Resolve, CapCut and iMovie as caption files, and by YouTube and Vimeo as uploaded subtitles.
Yes. The language is detected automatically; on this site 55 languages have been detected so far, with Spanish, French, Portuguese, Tagalog, German and Arabic the most common after English. A video that mixes languages is transcribed in the language that dominates.
With a free account the file runs on a GPU: a one-hour video is usually done in about five minutes. Without an account it runs in the standard queue, which takes roughly as long as the video and longer when the queue is busy.
With an account, yes: the online transcript marks each change of speaker as [SPEAKER_00], [SPEAKER_01] and so on, and the JSON export carries the same labels. Guest transcripts and the TXT, SRT and VTT files contain the text without speaker names.
The uploaded file is deleted from our servers automatically after 30 days. The transcript stays in your account until you delete it – you can delete a transcript and its file at any time. Files are processed automatically and are never shared.
transcribe.mov uses Whisper large-v3 (the turbo build) – the open model that OpenAI benchmarks per language. On read speech it makes roughly one error in 11 words in English and one in 18–21 in Spanish, German, Portuguese or Russian; clean studio audio is better, noisy or overlapping speech is worse, and independent tests of real meetings land around 11 % word error. You get the whole file, verbatim, with punctuation and speaker labels (registered users); you fix names and terms in the editor.
Record close to the speaker in a quiet room – one voice at a time transcribes best. Upload the original file; don’t re-encode or compress it (phone .m4a and camera .mov are fine as they are). Clear speech matters more than file quality: accents and cross-talk cost more accuracy than bitrate ever will. Silence and music are filtered automatically.
For a short clip you can. Gemini takes audio and video uploads, but its free tier stops at 10 minutes of audio or 5 minutes of video per prompt and needs a Google sign-in (3 hours of audio with a paid AI Pro plan). ChatGPT has no documented audio or video transcription feature: it may try on an uploaded file, and OpenAI itself says the analysis "may not analyze the entire video or accurately interpret its audio". In both, timestamps are written by the language model, not measured, so they drift, and there are no speaker labels on uploaded files. Here the video is transcribed in full and verbatim by a speech model, the SRT/VTT timing comes from the audio itself, speakers are labelled, files up to 10 minutes need no account at all, and your files are never used to train anything.
Facts updated August 2026
Sign up now to start transcribing your audio and video files with high accuracy, secure and private processing, and industry-leading features like speaker diarization and subtitle generation.
transcribe.mov - Free, Accurate, and Instant Transcription for Your Audios and Videos! Unlock the Power of Our AI-Powered Transcription Tool.
