Google releases Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, its "most expressive audio generation models yet", with support for more than 100 languages

You can now generate highly realistic and expressive custom voices for content creation at scale.

Google has introduced two new text-to-speech models, Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS. These models are designed to generate highly expressive and customizable audio. The Gemini 3.8 Flash TTS is aimed at creative direction and character design, allowing users to create entirely new voices from scratch using natural language prompts across over 100 languages and dialects. It also offers granular control over audio performance line-by-line. The Gemini 3.8 Flash-Lite TTS is optimized for high-volume, cost-efficient use cases such as dubbing and voice agents, with fine-grained control over tone and pacing. Both models support voice replication from short audio samples, and Google has integrated safety features like watermarking and consent verification. These new models are available through Google AI Studio, Gemini API, Gemini Enterprise, Gemini Notebook, and Google Vids.

The release of Gemini 3.8 Flash TTS and Flash-Lite TTS signifies a significant leap in generative audio capabilities, moving beyond basic voice synthesis to nuanced performance direction. The emphasis on granular, line-by-line control and the ability to create entirely bespoke voices from natural language prompts suggest a market shift towards highly personalized and dynamic audio content. This development directly impacts creators in gaming, audiobook production, and podcasting by offering tools that can dramatically reduce production complexity and cost while elevating audio quality and expressiveness.

These advanced TTS models are poised to democratize high-fidelity voice acting and sound design, making sophisticated audio production accessible to a broader range of developers and content creators. The integrated safety features, including SynthID watermarking and consent verification for voice replication, address growing concerns around AI-generated content authenticity and ethical use. As these technologies mature and become more widely adopted, we can anticipate a surge in innovative audio applications and a redefined landscape for voice talent and audio production workflows across various digital media.