Google DeepMind: Create your own voices with Gemini 3.8 text-to-speech
Google DeepMind's Gemini 3.8 text-to-speech technology enables users to design entirely new vocal personas for various applications like gaming, audiobooks, or podcasts. This can be done using natural language prompts to direct performance with nuanced acting cues, pacing, back-channeling, and dialect shifts. Alternatively, users can recreate consistent adult vocal profiles from a 30-second audio sample, provided they have the rights to use the voice. The system incorporates built-in consent verification, SynthID watermarking, and C2PA credentials to protect both developers and vocal talent. Users can learn more and start using the latest Gemini Audio models today.
Original sources
YouTube Google DeepMind
Video:Create your own voices with Gemini 3.8 text-to-speech ↗
AI Radar wrote this summary from the publisher’s notes with AI, not from a transcript. How it works.