On 23 September Google introduced Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS as its most expressive audio generation models yet. Developers and makers can generate custom character voices and direct scene dialogue across Google AI Studio, the Gemini API, Gemini Enterprise, Notebook and Google Vids. Flash-Lite targets high-volume work such as dubbing and agents; Flash supports richer direction and authorized voice replication from a short sample.
What changed is audio craft inside the same ecosystem many teams already use for decks and Vids cuts. Line-level control over pacing, dialect and delivery means the read becomes part of the edit, not a separate vendor hop. Peer coverage the same week framed the pair as cheaper and broader than prior Gemini TTS generations.
