Say hello to our new Gemini 3.8 text-to-speech models. Whether you need creative nuance or massive scale, build custom voice apps with more precise control using our most expressive models yet: 🔊 Gemini 3.8 Flash TTS: Designed for creatives, this model lets you use natural language to create custom vocal personas and direct cues, pacing, and dialects to build immersive apps and narrative games. 🔊 Gemini 3.8 Flash-Lite TTS: Built to scale high-volume audio pipelines, such as bulk audiobook production and audio dubbing. Try building with the new audio models now via the Gemini API in @​GoogleAIStudio.