Google Unveils Gemini 3.8 Flash TTS With Voice Cloning

Google has added two text‑to‑speech models to its Gemini AI collection: Gemini 3.8 Flash TTS and Gemini 3.8 Flash‑Lite TTS. These models give developers and users control over voices created by artificial intelligence. Users can make custom voices. If they have permission copy an existing voice.

The new models can generate voices based on natural-language prompts, allowing users to specify characteristics such as accent, role and vocal style. Google has also introduced voice cloning, which can reproduce a voice using a 30-second audio sample, provided the user has the necessary permission.

Gemini 3.8 Flash TTS availability

According to a Google blog post, Gemini 3.8 Flash TTS is available through the Gemini API and Google AI Studio for developers. Gemini 3.8 Flash-Lite TTS is also accessible through the Gemini API and Google AI Studio, as well as Google Vids. Google said availability across its various services may differ depending on the model, while support for the Gemini Enterprise API is expected to arrive later.

Google is also developing a voice remixing feature for Gemini 3.8 Flash TTS. The feature will allow users to take an existing voice and modify attributes such as pitch, timbre, accent and other vocal characteristics through natural-language prompts.

With Gemini 3.8 Flash TTS, users can create voices from scratch by describing the desired sound. The models support more than 100 languages and dialects, offering flexibility for applications requiring regional or multilingual voices.

For voice cloning, Google has added safeguards around consent. The company requires a consent recording from the voice owner before a voice can be replicated, while users must have permission to use the original audio sample.

Google also offers more than 2,000 ready-made voices for voice modulation, including regional varieties such as Mexican Spanish, Quebec French and Scots English.

The new Gemini 3.8 TTS models add to Google’s growing range of Gemini Audio capabilities, which includes Gemini 3.5 Live Translate, Gemini 3.5 Transcribe, Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking.

ABOUT THE AUTHOR

Kahekashan

[email protected]

Kahekashan is a passionate technophile with a keen eye for cutting-edge gadgets, emerging technologies, and everything in the digital realm. Raised in a Defence family with strong values and a background in literature, she has consistently pursued excellence in every endeavour. Her last full-time assignment involved content writing with the Indian School of Business.

Read More