# Google adds voice remixing to Gemini 3.8 TTS in the Gemini API

> Google's Gemini API now lets developers remix a prebuilt or designed voice with natural-language instructions to create a new stored voice.

- Status: official (From the company, authors or authority themselves, with a link to their own page.)
- Topic: Products
- Published: 2026-11-04T00:00:00+00:00
- Updated: 2026-11-07T11:33:06.315478+00:00
- Web page: https://ai-news.ikangai.com/story/google-adds-voice-remixing-to-gemini-3-8-tts-in-the-gemini-api/
- Seen in: Gemini API changelog
- Change: capability (New capability)
- Applies to: Gemini 3.8 TTS, POST /v1beta/voices, gemini-3.8-flash-tts, Gemini 3.8 Flash TTS, Gemini 3.8 Flash-Lite TTS

## What changed

Developers can now remix a prebuilt or designed Gemini 3.8 TTS voice with natural-language instructions to create a new stored voice in the Gemini API.

Google has added voice remixing for Gemini 3.8 TTS to the Gemini API, according to a changelog entry dated November 4. The feature starts with an existing voice, either prebuilt or designed, and modifies it based on natural-language instructions. The result is a new stored voice. The changelog says it is independent of the original, but it does not explain what that independence means in practice.

Developers can create a remixed voice by sending a request to the POST /v1beta/voices endpoint using the gemini-3.8-flash-tts model, or by remixing the voice interactively in Google AI Studio. Both routes produce a voice ID beginning with voice_. Developers then pass that ID when generating speech with Gemini 3.8 Flash TTS or Gemini 3.8 Flash-Lite TTS. The changelog does not say whether there are limits on how many voices can be stored or what the feature costs.

## Why it matters

Teams building speech products can now create custom stored voices through the API and reuse them across both the Flash and Flash-Lite TTS models. That removes the need to start from scratch for each new voice.

## What you can do

Developers using Gemini TTS can read the voice remixing guide and test the voices endpoint before planning a custom-voice feature.

## How the story developed

- 2026-11-07: Google's official changelog confirms the feature. It also lists the POST /v1beta/voices endpoint, the supported model names and the AI Studio option.

## Original source

- [Gemini API changelog: November 4, 2026](https://aistudio.google.com/docs/changelog)
- [Voice remixing](https://aistudio.google.com/docs/voice-remixing)

---

AI wrote this summary from the sources listed, and nobody reviewed it individually before publication. Check the original source before you rely on it.

Cite as: IKANGAI AI News, "Google adds voice remixing to Gemini 3.8 TTS in the Gemini API", 2026-11-04, https://ai-news.ikangai.com/story/google-adds-voice-remixing-to-gemini-3-8-tts-in-the-gemini-api/
