Google has introduced voice remixing features for its Gemini 3.8 Flash text-to-speech model. The update is currently accessible to developers and users through Google AI Studio and the Gemini API.
The new functionality enables users to adjust specific voice parameters via prompts. Available modifications include changes to timbre, pitch, pace, and accent, expanding the customization options for the model.
The Gemini 3.8 model was released for general availability in September 2026. This update serves as a key enhancement to Google's primary text-to-speech offering within its AI ecosystem.
Industry analysts are tracking these developments as part of the broader competition in the AI sector. Future performance benchmarks on the Chatbot Arena LLM Leaderboard are expected to reflect these changes.
