Google turns on Voice Remixing for Gemini 3.8 Flash TTS
Google announced on November 4, 2026 that Voice Remixing is now live for Gemini 3.8 Flash's text-to-speech system, available in Google AI Studio and the Gemini API.
·1 min read·AB
Google @Google
Voice Remixing for Gemini 3.8 Flash TTS is now live in @GoogleAIStudio and the Gemini API.
Start with a preset from our library of 2,000+ voices or a custom-designed voice, and use prompts to fine-tune timbre, pitch, pace, and accent, like "add a subtle Southern U.S. accent" or… pic.twitter.com/IixWu8wZV6
Google announced on November 4, 2026 that Voice Remixing is now live for Gemini 3.8 Flash's text-to-speech system, available in Google AI Studio and the Gemini API. Text-to-speech systems convert written text into spoken audio, and voice remixing extends that by letting a single voice be adjusted after the fact through prompts rather than re-recorded. Developers can start from a library of more than 2,000 preset voices or bring a custom-designed voice as a base.
From there, prompts let developers fine-tune the voice's timbre, pitch, pace, and accent, for example asking for 'a subtle Southern U.S. accent' or telling it to 'sound like a fire-breathing dragon.' Google's announcement included a demo video showing the feature in action, highlighting how a single base voice can be reshaped into many variations through natural-language instructions instead of separate recordings for each one.
Why it matters
Prompt-based control over timbre, pitch, pace, and accent gives developers far more flexibility in generating custom synthetic voices.
Source: Google