How it works
Click Record. If the speech model is already saved on your device, captions appear every few seconds while you talk. When you stop, the whole recording is transcribed again in one pass, which gives the most accurate final text with timestamps.
The first time, transcribe any file or recording so the model is saved. After that, live captions start immediately, even offline.
Good uses
- Checking that the microphone is picking you up before a long session.
- Following along in a lecture or talk.
- Dictating notes and seeing them form as you go.
Tips
- Choose the spoken language instead of automatic detection for faster, steadier captions.
- Balanced is a good choice for live captions; Accurate is better for the final transcript on a fast computer.
- Keep the tab open while recording.
What happens to your recording
Your browser reads the file from your device and runs the speech model locally. The audio, the video and the transcript are never sent to a server, so there is nothing for us, or anyone else, to store, train on or lose in a breach. Finished transcripts are saved only in your browser’s storage, where you can export or delete them in your library. The only thing that comes from the internet is the speech model itself, once. You can check this by turning off Wi-Fi after the first transcript: it keeps working.