Transcribe audio and video to text
Speech to text and subtitles made by an AI model running in this tab. Interviews, lectures and voice notes are never uploaded.
- Nothing is uploaded
- Works offline after first use
- Open source
- No watermark · limit is your device’s memory; phones hold less
Turns speech in an audio or video file (MP3, WAV, M4A, MP4, MOV) into text, SRT subtitles or WebVTT captions with Whisper, in 16 or more languages. It is free, needs no account and adds no watermark, and your files are not uploaded: everything runs in your browser on your device. The first run downloads the speech model (about 76 MB) and the WebAssembly engine that runs it to your browser, and after that the tool works offline.
Done
Open the network tab. Your files never appear in it.
Add files and run the tool to see every request this tab makes.
Your files are processed on this device and never sent to a server. Reload the page to clear everything from memory.
How it works
- Drop one or more recordings or videos.
- Pick the spoken language (or let it detect it), and whether you want text, SRT subtitles or WebVTT captions.
- Press Transcribe. The first run downloads the speech model and its engine once; the transcript appears with a Copy button and downloads as a file.
In your browser, not on a server
Your browser’s own decoders read the sound, from an audio file or a video’s soundtrack, and it is resampled to 16 kHz mono in the tab. The recording is cut at pauses into pieces of up to 28 seconds, and each piece goes to OpenAI’s Whisper base model (MIT), 8-bit ONNX weights run by transformers.js (Apache-2.0) and onnxruntime-web (MIT) in a background worker. The model, 76 MB, is downloaded from this site on first use and cached. Its timed segments become paragraphs, SRT or WebVTT.
Compared with upload-based tools: Online transcription services upload the recording to their servers, cap free minutes, and some keep your audio to train their models. Here the model runs on your device: nothing is uploaded, there is no minute limit beyond your device’s memory (phones hold less), and it works offline after the first run.
Verify it yourself. Give the page a short while after your first run to save itself for offline use, then turn off Wi-Fi or switch to airplane mode and run the tool again. Or open your browser's developer tools (F12, or Cmd-Option-I on a Mac), pick the Network tab, and watch it while you convert. The panel above does the same count for you.
Questions
Is my recording uploaded?
No. The sound is decoded in this tab and the Whisper speech model runs in your browser, so interviews, medical dictation, meetings and voice notes stay on your device. What gets downloaded is the speech model and the engine that runs it, both from this site, the first time.
How accurate is it?
This is Whisper base, OpenAI’s small multilingual model, compressed to run in a browser. Clear speech in English and other widely spoken languages comes out well; strong accents, crosstalk, music and technical names cause mistakes. Read the transcript through before you publish it.
How long does it take?
It depends on your device. On a recent laptop, ten minutes of sound takes about two to three minutes, plus a few seconds to load the model; on a phone it is several times slower. Keep the tab open while it works.
Can it make subtitles for a video?
Yes. Choose Subtitles (.srt) for YouTube, Premiere, DaVinci Resolve, VLC and most players, or Web captions (.vtt) for a web page’s track element. Each caption is timed to the speech.
Does it tell speakers apart?
No. It writes what is said, not who said it. Long pauses start a new paragraph in the text version, which usually falls where the speaker changes.
Can I turn a video into text?
Yes. Drop an MP4, MOV, M4V, MKV or WebM file and choose Text (.txt): only the soundtrack is read, in this tab, and the video is not uploaded. For a recorded lecture or a Zoom MP4 there is a page set up for it, Video to text. For timed captions instead of paragraphs, use Video to subtitles; for sound-only files, Audio to text.
More video and audio tools
Add subtitles to video
Captions written from the speech and burned into the picture, on your own device. Or bring an SRT and burn in that.
Vocal remover
Split a song into the music and the voice with an AI model running in this tab. Karaoke tracks and acapellas without uploading anything.
Video background remover
The person stays, the room goes: blurred, a flat colour or a picture of your choice, done frame by frame on your own device.
Audio splitter
Cut one long recording into separate files at the times you choose or at equal lengths. Done on this device, and the file is not uploaded.
Popular conversions
Guides
- How to transcribe audio to textEvery platform has a way to turn speech into text now, at very different prices. Here is what each one offers, and a free option that never uploads the recording.
- A free Otter.ai alternative with no monthly minute capOtter.ai's free tier meters your minutes each month and caps how long a single recording can run. Here is what that looks like, and an alternative with nothing to meter.