Google Launches Gemini TTS Models With 2,000+ Voices Across 100 Languages

Google has introduced Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, expanding its text-to-speech capabilities for developers and creators. The models offer access to more than 2,000 voices across 100 languages, along with tools for creating customized voices through natural-language prompts.

Gemini 3.8 Flash TTS is designed for creative applications where expressive and dynamic audio matters. Potential use cases include audiobooks, games, interactive experiences and multi-character storytelling. Developers can also create multi-speaker scenes, making conversations and narrative audio more natural.

The Flash-Lite version focuses on efficiency and high-volume workloads, making it suitable for applications such as large-scale dubbing and other content production tasks where speed and cost efficiency are important.

Google says both models performed strongly across its evaluations, including ranking first for pronunciation robustness. The models are already available through Google AI Studio and the Gemini API, giving developers access to the technology for experimentation and production use.

For marketers, creators and media companies, advanced TTS could significantly simplify voice production. Instead of recording every variation manually, teams can generate multilingual voice content and experiment with different characters and styles through prompts.

The bigger opportunity is the combination of AI-generated voices, multilingual support and scalable production, potentially making personalized audio content easier and faster to create.

Source: Google