MP3 · M4A · WAV · MP4
Drop in your files
Open the side panel and drag in up to five recordings at once — meetings, interviews, voice memos, lectures.
MP3 to Text Add to Chrome
English
Runs on your device
Audio to text, without the upload
A Chrome extension that turns MP3, M4A, WAV and MP4 into text on your own machine. No upload, no account, no server — and a faster cloud pass only when you ask for it.
Free · No account · Works offline after the first run
Works with
- MP3
- M4A
- WAV
- MP4
- OGG
- FLAC
- AAC
- WEBM
How it works
Three steps, and the second one happens on your own hardware.
Runs on your device
Transcribe on device
The speech model runs in your browser. Long recordings are split into windows and transcribed in order, with progress you can watch.
TXT SRT
Copy or export
Take the text straight to your document, or export SRT when you need timed subtitles.
Local transcription
Your recording never leaves the machine
The model downloads once and then runs entirely in your browser. After that first download, transcription works with the network off — on a plane, in a meeting room, anywhere.
- No upload, no account, no server round-trip
- Works offline once the model is cached
- Audio, transcripts and job state stay in your browser profile
team-sync.mp3 Runs on your device
00:04 The speech model runs in your browser. Long recordings are split into windows and transcribed in order, with progress you can watch.
00:26 No upload, no account, no server round-trip
01:12 Works offline once the model is cached
TXTSRT200 MB
Output
Text you can actually use
Plain text for documents and notes, SRT when the recording needs subtitles. Long jobs keep running while the panel is closed, and tell you when they are done.
- Export as TXT or SRT, or copy straight to the clipboard
- Batch up to five files in one run
- Background jobs survive a closed panel and a browser restart
Output SRT
1 00:00:04,120 → 00:00:08,640
Take the text straight to your document, or export SRT when you need timed subtitles.
2 00:00:08,640 → 00:00:13,200
Export as TXT or SRT, or copy straight to the clipboard
Built for real recordings
Not a demo that handles thirty clean seconds — a tool for the hour-long meeting you actually have to write up.
Files up to 200 MB
Long meetings, full lectures and field recordings, not just short clips.
Five files at once
Queue a batch and let it work through them in sequence while you do something else.
Multilingual
The model detects the spoken language on its own — no picking from a dropdown first.
Optional Pro pass
When a recording is hard, send that one file for a faster, more accurate cloud run. Never automatic.
No permissions creep
No host permissions at all: the extension cannot read the pages you browse.
Nothing to sign up for
No account, no email, no trial that expires. Install it and drop a file.
Privacy
Private by architecture, not by promise
Most transcription tools ask you to trust a privacy policy. This one mostly cannot break the promise: the work happens in your browser, and the extension has no permission to reach the pages you visit.
- No upload, no account, no server round-trip
- No host permissions at all: the extension cannot read the pages you browse.
- Audio, transcripts and job state stay in your browser profile
What a local run does
Audio uploaded None
Account required No
Network after model download Not needed
Host permissions None requested
Usage analytics Optional, off in one switch
Questions
Is my audio really not uploaded?
On a local run, no. The file is decoded and transcribed inside your browser. The optional Pro pass is the only mode that sends audio anywhere, and it only ever sends the one file you picked for it.
Why is the first run slow?
The speech model downloads once, which takes a minute on a normal connection. It is cached afterwards, and every later run starts immediately — with or without a network.
How long can a recording be?
Files up to 200 MB. Long recordings are split into windows and transcribed in sequence, so a one-hour meeting works the same way a two-minute memo does, it just takes longer.
Which formats can I use?
Anything your browser can decode, which covers MP3, M4A, WAV, MP4, OGG, FLAC, AAC and WEBM. Output is plain text or SRT subtitles.
What does the Pro pass cost?
Local transcription is free and unlimited. The Pro pass is a paid pack of minutes for when you want the faster, more accurate cloud model on a specific file.
Put the transcript where it belongs: on your machine
Install the extension, drop in a recording, and read the text before anything has had a chance to leave your device.
Add to ChromeFree · No account · Chrome 116 and later