Transcribe video to text.
Transcribe video or audio to text in under a minute — every line editable, SRT and VTT ready to export.
MP3 · M4A · WAV · FLAC
Free · 3 files a day · up to 30 minutes each · no account · need more? buy a pack
Longer than 30 minutes? Extract the audio first, or split the file into two.
You've used your 3 free files today. Buy a pack to keep going now.
Welcome back to the show. Today we're talking about how small teams ship fast, without burning everyone out.
Thanks for having me. I think the honest answer is that most of it comes down to deleting work, not adding it.
Say more about that — what do you actually delete?
Meetings, mostly. And any feature that needs a paragraph of explanation before you can use it.
That sounds like a high bar. Doesn't it kill good ideas before they get a chance?
It kills the ones that were going to be explained forever. The ones worth keeping explain themselves in a screenshot.
So what does a week look like when you're doing this well?
Monday we decide what not to build. Tuesday through Thursday we build the one thing left. Friday we watch people use it and write down what confused them.
And the writing down part matters more than people think?
Much more. A bug report you can quote is worth ten meetings about how something feels off. That's why we record the calls and transcribe them — the exact words are the evidence.
Three things that make it usable.
Your video is never uploaded. The audio track is extracted in your browser; only a ~5 MB audio file leaves the machine.
Languages, detected. English, Spanish, Mandarin, Arabic, Hindi. No dropdown, no wrong guess to correct afterwards.
Exports, all free. TXT for reading, SRT and VTT for YouTube or any editor, timestamps intact.
How to transcribe video to text in three steps
- Drop a file. Your browser reads the video and extracts the audio track. The video itself never leaves your computer, which is why a 400 MB file is ready in seconds — it was never uploaded.
- We transcribe the audio. The compressed audio track goes to our server, runs through a speech model, and comes back as timestamped segments. A 10-minute file is usually done before you switch tabs.
- You edit and export. Fix a name, label the speakers, then take the transcript as TXT, SRT or VTT. Nothing is kept on our side once the request finishes.
Supported video and audio formats
| Video | Audio | |
|---|---|---|
| Formats | MP4, MOV, MKV, WebM, AVI | MP3, M4A, WAV, FLAC, OGG, AAC |
| Free tier | up to 30 min · 500 MB · 3 files/day | same |
| Export | TXT, SRT, VTT — free | same |
| Languages | 100+, detected automatically | |
What people transcribe
- Videos → text. Interviews, lectures, webinars, screen recordings — turn any video into a searchable transcript. Upload it to YouTube as captions and the video starts ranking for phrases people actually said in it.
- Podcasts → text. Publish episodes as blog posts, or pull quotes without scrubbing through audio. An hour-long episode comes back with timestamps you can cite and link to.
- Meetings → text. Record the call, drop the file, keep decisions and action items in writing. Nobody has to take notes, and nobody argues later about what was agreed.
Why the file is processed on your device
Most online converters upload the whole video to a server, which means waiting for a 500 MB file to travel twice and trusting someone else's storage with it. Verbatimly only needs the audio track, and the audio track can be made locally. That single decision is why the upload step takes a second instead of ten minutes, why nothing has to be cleaned up afterwards, and why the service can stay free for occasional use.
SRT or VTT? Which one you need
SRT
The safe default. Every video platform, editor and player reads it: YouTube, Premiere, Final Cut, DaVinci, VLC. If you are uploading captions somewhere, start here.
VTT
What the web uses. HTML5 video players take VTT natively, and it supports styling and positioning that SRT does not. Pick VTT if the video lives on your own site.
Both are plain text with the same timestamps. Convert between them by renaming the file and swapping commas for periods — or export both here, they are both free.
Putting the transcript on YouTube
- Export SRT from the transcript toolbar.
- Open YouTube Studio, go to Subtitles, pick the video and choose Add language.
- Select "Upload file" then "With timing", and choose the .srt you downloaded.
- Check the first and last line in the editor. If the sync drifts, re-upload rather than nudging line by line.
YouTube accepts SRT, VTT and SBV. Uploaded captions are indexed by search, so the video starts showing up for phrases people actually said in it.
Questions people actually ask.
Is it really free?
Yes. Three files a day, up to 30 minutes each, no account required. The transcript, every export and speaker labelling are free. A credit pack is the only paid product: it adds 5 more files that do not expire and raises the limit to 60 minutes per file. There is no subscription and no batch upload.
Do I need to sign up?
No email, no account, no card. Drop a file and take the transcript.
Which formats work?
MP4, MOV, MKV, WebM and AVI for video; MP3, M4A, WAV, FLAC, OGG and AAC for audio. If a MOV fails to decode, export it as MP4 first.
How long can a file be?
Free: up to 30 minutes and 500 MB per file. With a credit pack: up to 60 minutes and 500 MB per file.
How fast is it?
Transcription runs on our servers, so there is no AI model to download and nothing to install. A 10-minute video is usually done in under a minute.
Can it tell who is speaking?
You can label speakers yourself: click the S tag on any line to cycle Speaker 1, 2 or 3. The labels carry into SRT and VTT exports. Automatic detection is not offered.
Can I export subtitles?
Yes — TXT, SRT and VTT files are all free, ready to upload to YouTube or any video editor.
What happens to my files?
We do not store your uploads. The audio is processed and discarded, and the transcript is returned to your browser only. Nothing is used to train models or reviewed by a person.