Google releases Gemini 3.8 Flash TTS with voice design
Gemini 3.8 Flash TTS and Flash-Lite TTS let creators design new voices from a text prompt and direct dialogue line by line in over 100 languages. They are available in Google AI Studio, the Gemini API and Google Vids, and every clip is watermarked with SynthID.
What it does
Gemini 3.8 Flash TTS lets you design a new voice from a text description (role, accent, character) in more than 100 languages, or pick from 2,000+ ready voices. You direct delivery line by line with stage directions, and it can stage two-speaker scenes from one script and hold a voice steady over hours of audio.
Flash-Lite TTS targets high-volume dubbing and voice agents.
Results and limits
Google says Flash TTS ranks #1 on Hume AI's Voice Design Benchmark (71.4), and Flash and Flash-Lite rank #1 and #2 on Hume AI's Overall Quality Index. Voice replication from a 30-second sample requires a recorded consent statement from the voice owner.
Worth knowing
It's available in Google AI Studio, the Gemini API and Google Vids, with Gemini Enterprise coming. Every clip is watermarked with SynthID. Voice replication isn't available in Illinois, Texas, the EEA, the UK, Switzerland or India.
Try it yourself
In Google AI Studio, design a voice: "[age] [role] with a [regional accent], [texture, e.g. gravelly], [pace]." Then in the two-speaker editor: "[Speaker A]: [line] / [Speaker B, whispering]: [line]".