Record, clean, edit, and transcribe podcast audio in a browser without installing a desktop editor.
Audio & Voice

Gemini 3.1 Flash TTS generates expressive multi-speaker speech with natural-language control over tone, pacing, and emotion.
Best for: Creating multilingual narration, Producing multi-speaker dialogue, Testing expressive voice directions
Record, clean, edit, and transcribe podcast audio in a browser without installing a desktop editor.
Turn a video, social link, or audio file into a transcript, subtitles, and a summary.
Generate expressive speech and clone an authorized voice locally with an efficient open-source TTS model.