Free tool · No sign-up · Speaker labels
Upload a Zoom, Google Meet, or Teams recording — or record the meeting as it happens — and get an accurate transcript with timestamps and who said what. No account, no trial clock — just a 30-minute cap so it stays free for everyone.
Drop an audio or video file
or browse · MP3, WAV, M4A, OGG, FLAC, MP4, MOV
Free for recordings up to 30 minutes, about 3 hours of audio a day. Deleted as soon as it’s transcribed.
Works in current Chrome, Edge, Safari, and Firefox, phones included. Nothing to install.
How it works
The whole thing happens on this page. There’s no queue, no email with a link later, and no bot to invite to the meeting first — you already have the recording, so this is the part that turns it into text.
The MP4 Zoom saved, the recording Google Meet or Teams dropped in your drive, a phone recording of a call, or the audio track of any video. Or hit Record and capture the meeting as it happens. Up to 30 minutes.
The same engine that powers Assistly on live calls transcribes it, labels who said what, and detects the language. Your audio is deleted the moment the text is back.
Read it as a script or as timestamped lines you can click to replay. Copy it, or download TXT, SRT, or VTT subtitles.
What people bring
Zoom, Google Meet, Microsoft Teams, Webex, a phone on the table — if it saved a recording, it’s a meeting transcript a minute from now. MP3, WAV, M4A, OGG, FLAC, MP4, and MOV all work as they are; only the audio track of a video is sent on.
Every call app saves a recording; none of them hand you a clean transcript for free. Upload the MP4 or M4A and get one, with each participant labelled.
Hiring loops, customer calls, journalism. The transcript reads as a script, one paragraph per turn, so you can quote people accurately.
Record the room from a phone and turn it into minutes. Timestamps let you jump back to the moment a decision was made.
A recorded session becomes searchable notes. Dozens of languages are detected automatically, even when the speaker switches mid-sentence.
Talk through your notes on the way back from a meeting and paste the text into your doc, ticket, or CRM a minute later.
Export SRT or WebVTT with timestamps for the highlight you're sharing with the team, or for a YouTube upload of the webinar.
Why it’s free
Assistly already pays for a transcription engine to run live on your calls. Lending it out for recordings under thirty minutes costs us cents per file — so instead of a meter, there’s a limit.
Every line says who said it, so a meeting comes back as a script, not a wall of text. That's the part most free meeting transcription tools charge for.
Your audio goes over an encrypted connection to the engine and is deleted the moment the transcript is back. We don't store recordings or text, and nothing trains a model.
The language is detected automatically — even when speakers switch mid-sentence — and punctuation, names, and numbers come through cleanly.
Choosing a tool
A meeting is the hardest audio there is: several people, one laptop microphone, and the important sentence said over someone else. Here is what to check in any transcription tool, free or paid — and how this one answers.
Speaker 1, Speaker 2, and so on, on every line — automatic, no training the tool on voices first.
Each line is anchored to the recording. Tap a timestamp and it plays from there, the fastest way to verify a quote.
Plain text, SRT, and WebVTT with no watermark and no paywall on the download button.
Nothing joins the call or appears in the participant list. You transcribe a recording you already have, made with the consent your meeting already required.
Crosstalk, accents, laptop microphones, and phone-quality lines are what meetings sound like. The engine was chosen on exactly that audio.
Encrypted in transit, deleted on completion, never used for training. The same terms the Assistly app runs on, written into the privacy policy.
FAQ
It's free, with no account, no trial minutes, and no watermark. The limits are the catch, and they're simple: one recording can be up to 30 minutes, and each person gets about three hours of audio a day. That's enough for a stand-up, an interview, a lecture, or a short meeting. We run it because people who need a meeting transcript today are often the same people who'd like the transcript written while the meeting is still happening — which is what Assistly, our desktop app, does with the same engine and no cap.
Yes. Zoom saves local recordings as MP4 and M4A, Google Meet and Teams save MP4 to your drive, and Webex saves MP4 or ARF (convert ARF to MP4 first). Upload the file as it is: the audio track is separated out on our side, so a large video costs nothing more than its minutes. Each participant comes back labelled Speaker 1, Speaker 2, and so on. There is no bot to invite, no calendar integration, and no plug-in — this is for the recording you already have.
If anyone recorded it, drop the recording here and you'll have the transcript in about a minute, with timestamps and speaker labels. If nobody recorded it, no tool can recover it — which is the case for using something during the meeting. Assistly, the desktop app behind this tool, transcribes calls live, with no bot in the participant list, and writes the recap and action items when you hang up.
Your file is sent over an encrypted connection to our server, which checks it and passes it to our transcription provider, Soniox — the same engine the Assistly app uses live. The transcript comes back to your browser, and the audio and transcript are deleted from the provider the moment your browser has received it. We don't store the recording or the text, we never see them, and nothing is used to train AI models. If you'd rather nothing left your computer at all, this isn't the tool for you — a locally installed transcriber is.
Yes. Every line is labelled Speaker 1, Speaker 2, and so on, and the text view reads like a script — one paragraph per turn. That's what makes it a meeting transcript rather than a wall of text. The labels are automatic and occasionally a quick back-and-forth gets merged; the timestamped view lets you replay any line to check.
Any common audio or video file up to 30 minutes and 500 MB: MP3, WAV, M4A/AAC, OGG, FLAC, Opus, and WebM audio, plus the soundtrack of MP4 and MOV video — a phone video is fine as it is; only its audio track is sent on for transcription. You can also record straight from your microphone, which works for a meeting happening in the room with you.
Very — this is the engine we chose for our own product after testing the alternatives on the audio meetings actually produce: several people, laptop microphones, crosstalk, phone-quality lines. The free tool uses it unchanged. It punctuates properly, handles accents well, and recognises dozens of languages, switching mid-sentence if the speakers do. It detects the language automatically; naming it in the picker helps on very short clips.
Because every minute costs us money and the tool has no sign-up, a cap is what keeps it free for everyone rather than exhausted by a few scripts. Thirty minutes covers most of what people bring to a free tool. For a full-length meeting, split the recording in two, or let Assistly transcribe the meeting live as it happens, with no cap, and write the recap and action items when you hang up.
Current versions of Chrome, Edge, Safari, and Firefox, on desktop and on phones. Nothing is downloaded or installed — the work happens on our side — so an older phone is as fast as a new laptop. Recording from the microphone needs the browser's permission, which it asks for when you press Record.
Yes. Once the transcript is ready you can copy it, download it as plain text (with speaker labels when there's more than one speaker), or download it as SRT or WebVTT subtitles with timestamps — the formats video editors, YouTube, and media players expect. Click any timestamp on the page to play the recording from that point.
The live version
The desktop app follows your meetings, sales calls, and interviews as they happen — the answer is on your screen while the question is still being asked, every speaker kept straight, and the recap with action items is waiting when you hang up. No bot joins the call, and there’s no 30-minute cap.