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.
Voice memos, recorded meetings, lectures, dictations, calls – upload the recording and read it as text. Recordings up to 10 minutes are free without an account; with a free account you get 30 free minutes, speaker labels and faster processing, then you pay per minute – no subscription. One in six files uploaded here is an M4A voice memo, and most recordings are short: half are under two and a half minutes.
Straight from your phone: iPhone Voice Memos (M4A), Android recorders (M4A, AAC, MP3), Zoom and Teams recordings (MP4, M4A).
Speaker labels: with a free account, meetings and interviews come back with each speaker marked.
Timestamps when you need them: plain text, or SRT/VTT with the time of every line.
Language detected automatically: a memo in Portuguese or German needs no setting; 55 languages detected on this site so far.
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: M4A, MP3, WAV, AAC, OGG, FLAC, MP4 · Prices
Six in ten recordings from paying users are a single voice – memos, dictations, lectures – and average under four minutes. Longer ones with two or more people are labelled by speaker automatically.
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 and one in 17 in Portuguese and Russian. 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.
iPhone Voice Memos saves M4A (AAC audio); Android recorders write M4A, AAC or MP3 depending on the app; dedicated recorders from Zoom, Tascam and Sony write WAV or MP3; Zoom and Teams save meetings as MP4 with a separate M4A audio file. All of these upload as they are – nothing has to be converted.
A voice memo is small: an hour of M4A is roughly 30–60 MB, so a ten-minute memo fits the guest limit of 50 MB easily. WAV from a field recorder is ten times larger – about 600 MB per hour – which is what the 4 GB limit for account holders is for.
Distance to the microphone matters most: a phone on the table in a quiet room transcribes very well, a phone in a pocket or across a large room does not. Echo, traffic and several people talking at once are the other causes of corrections. Recording in a normal voice and keeping the phone within arm’s reach is worth more than any setting.
Four lines from a recorded meeting as the online transcript shows them with “Show Timecodes” and “Show Speakers” switched on. The labels are generated automatically; the JSON export carries them too.
[00:00:00 --> 00:00:06] [SPEAKER_00] Let’s go through the open items. First, the venue for October. [00:00:06 --> 00:00:11] [SPEAKER_01] I have two quotes. The second one includes the catering. [00:00:11 --> 00:00:15] [SPEAKER_02] Then that’s the one. Can you confirm it by Friday? [00:00:15 --> 00:00:18] [SPEAKER_01] Yes, I’ll send the confirmation tomorrow.
The TXT download contains the same text without the labels; SRT and VTT add the time of each line.
Open Voice Memos, tap the recording, tap Share, then either “Save to Files” and upload it from there, or share it straight into your browser. The M4A file is accepted as it is.
Yes. Upload the MP4 or the M4A audio file the meeting tool saved. With a free account the transcript marks the speakers, so the meeting reads as a dialogue rather than one block of text.
A phone on the table in a quiet room transcribes very well. Distance, echo, background noise and people talking over each other lower the accuracy – the closer the microphone to the speaker, the less you correct afterwards in the editor.
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. After that you buy minutes: 120 for $5.90, 300 for $10.90, 600 for $19.90 – one-time, no subscription, and the minutes never expire.
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 labels. Guest transcripts and the TXT, SRT and VTT files contain the text without speaker names.
Yes. The language is detected automatically – 55 languages so far on this site, with Spanish, French, Portuguese, Tagalog, German and Arabic the most common after English.
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. Nothing is 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 recording 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.
