What you can do
- Write a summary. Key points of the whole recording, built in parts for long transcripts.
- Ask a question. For example "What did the client say about the deadline?" The answer comes only from the transcript.
- Translate the transcript into about 30 languages, then download it as Word, TXT, SRT or VTT with the original timings.
What you need
These features use the AI built into Chrome and Edge, version 138 or newer, on a Windows, Mac, Linux or ChromeOS computer. The browser downloads its model the first time you use it, then it works offline. Phones and other browsers still get key points, topics, YouTube chapters and a show notes draft, which work everywhere.
Accuracy
A summary is only as good as the transcript under it, so proofread names and numbers first. For decisions, quotes and anything legal or medical, check the answer against the transcript and the audio.
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.