Gemini 3.8 text-to-speech says hello

Google has introduced two new text-to-speech models as part of its Gemini AI family, allowing creators, developers, and enterprises to craft rich, expressive audio experiences. These models, Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, enable users to customize voices, from accent to emotional tone, with unprecedented control.

Both models outperform previous versions in voice customization, accent modeling, and overall quality, securing top positions on Hume AI's Voice Design Benchmark and Overall Quality Index. With support for over 100 languages, these models empower creators to build high-quality, multilingual voice experiences worldwide. Google's new voice generation tools come with strict safeguards, including consent verification for voice replication and watermarks to prevent AI-generated speech from being used to spread misinformation.