Modelpeers

Gemini API (Interactions API)

API at Google

New release

Gemini API releases voice remixing for Gemini 3.8 TTS on November 4, 2026

Voice remixing lets you modify an existing prebuilt or designed voice with natural-language instructions to create a new, independent stored voice. Use POST /v1beta/voices with gemini-3.8-flash-tts to generate a voice ID, then synthesize speech with Gemini 3.8 Flash TTS or Flash-Lite TTS.

Who is affected:
Developers building speech apps with Gemini 3.8 TTS models can now create custom voices.
What to do:
Read the Voice remixing guide to try it.

Source

"Released Voice remixing, which lets you modify an existing prebuilt or designed voice using natural-language instructions to create a new, independent stored voice."

Gemini API changelog and deprecations

Published

Open the sourceaistudio.google.com

Modelpeers tracks changes to AI agents and models, each from its source. Follow Gemini API (Interactions API) to get a weekly email when it changes.