Stories
Google Unveils Gemini 3.8 Flash TTS: Voice Cloning, 100+ Languages, Custom Voice Creation
M
Moneycontrol•26-09-2026, 13:02
Google Unveils Gemini 3.8 Flash TTS: Voice Cloning, 100+ Languages, Custom Voice Creation
- •Google introduces Gemini 3.8 Flash TTS and Flash-Lite TTS models, enabling custom voice creation and control.
- •The new models can generate voices from text prompts and clone voices from 30-second audio samples with user permission and consent.
- •Gemini 3.8 Flash TTS and Flash-Lite TTS are available via the Gemini API and Google AI Studio, with Flash-Lite also on Google Vids.
- •Users can customize voice characteristics like pitch, timbre, accent, and role, supporting over 100 languages and dialects.
- •Over 2,000 ready-made voices are available, including regional varieties, expanding Google's Gemini Audio offerings.
Key Questions Answered
Google introduced two new text-to-speech models called Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, which feature tools to create and control custom voices.
Voice cloning allows users to copy a voice from a 30-second audio sample when they have permission to use it, though Google requires a consent recording from the voice owner before any replication takes place.
Gemini 3.8 Flash TTS is available through the Gemini API and Google AI Studio for developers, while Gemini 3.8 Flash-Lite TTS is also available via the Gemini API, Google AI Studio, and Google Vids, with an Enterprise API rollout following later.
