Google launches Voice Remixing for Gemini TTS: 2,000+ preset voices, prompt-designed custom voices
goyalshaliniuk · x · 2026-11-07
Google launched Voice Remixing for Gemini 3.8 Flash TTS, now live in Google AI Studio and the Gemini API. New capabilities include:
- Choose from 2,000+ preset voices
- Create custom-designed voices via text prompts
- Adjust pitch, tone, timbre, and speaking pace
- Fine-tune accents with simple text prompts
- Experiment with creative voices from natural human speech to fantasy characters like fire-breathing dragons
Content creators and developers can now describe the voice they want, refine it with prompts, and iterate instead of settling for generic AI voices.
More from Multimodal
- Local pipeline showcase: MiniMax H3 refMod generations from reference image to 4K upscale — edisson75 · 2026-11-13
- Gaussian splats may be the best way to capture how 3D displays like LKG Portrait look IRL — nptacek · 2026-11-13
- AI-generated 'not canon' clip of Schwarzenegger driving with Michael Jordan — alanskimp · 2026-11-13
- H3-Image API gotcha: server keeps billing on client timeout — set max_retries=0 — xiaohu · 2026-11-13
- MiniMax open-sources H3-Image: native 16MP output, up to 16 reference images — xiaohu · 2026-11-13
- Daily AI painting made with GPT-6 Images 2.6 shows painterly winter village — DeryaTR_ · 2026-11-13