From the source
Google DeepMind's gemini-3.5-transcribe and gemini-3.5-transcribe-live now support voice-driven editing, rewriting and formatting of dictated speech or pre-existing text.
- The change lets users edit text by voice rather than typing, and applies both to speech the models transcribe and to text supplied as source_text.
- Google points readers to its Audio transcription and Live transcription guides for details.




