Google introduces Flash TTS models for customizable AI voices
Google has introduced Gemini 3.8 Flash TTS and Flash-Lite TTS, two speech-generation models supporting more than 100 languages. Flash TTS can create a voice from a text description specifying characteristics such as role, accent and vocal qualities. Users can also choose from more than 2,000 preset voices, including regional variants. A cloning function creates a voice profile from a 30-second recording, but the speaker must provide a matching spoken consent statement. Google says generated audio includes an inaudible SynthID watermark.
Both models accept directions for individual lines, including delivery, pauses and reactions. They can produce two-person dialogue from one script while keeping the voices separate, as well as sounds such as laughter, sighs and “mhm.” Google says they can generate hours of audio with limited speaker drift. A planned Voice Remixing feature will adjust timbre, pitch, tempo and accent of library voices, but is not yet available.
Flash TTS targets podcasts, audiobooks and game characters, while Flash-Lite TTS is intended for lower-cost, large-scale dubbing, audio content and voice agents. The models are rolling out through the Gemini API and Google AI Studio; Flash TTS is also in Gemini Notebook and Flash-Lite TTS in Google Vids. Enterprise API access is planned.
Written by Sakhanda Wire AI from reporting by The Decoder. Facts, quotes and full context are in the original article below.