Google DeepMind has introduced two new text-to-speech models to its Gemini family: Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS. According to the company, these are its most expressive audio generation models to date, designed to move voice generation from static presets toward a dynamic creative studio for creators, developers, and enterprises.
The two models serve different needs. Gemini 3.8 Flash TTS is built for deep creative direction and character design, allowing users to create entirely new voices from natural language prompts and direct performances line by line with control over acting cues, pacing, dialect shifts, and backchanneling. Gemini 3.8 Flash-Lite TTS targets high-volume, cost-efficient scale, optimized for dubbing, audio content creation, and expressive voice agents.
Key capabilities include generative voice design across more than 100 languages and dialects, access to a library of 2,000+ production-ready voices, and voice replication from a 30-second audio sample. The company says replication is backed by consent verification, SynthID watermarking, and C2PA credentials. A voice remixing feature for fine-tuning timbre, pitch, pace, and accent is described as coming soon.
On performance, Google DeepMind says Gemini 3.8 Flash TTS took the #1 overall spot on Hume AI's Voice Design Benchmark (71.4) and led in accent modeling (60.8). The two models also secured the #1 and #2 spots respectively on Hume AI's Overall Quality Index, with improvements over Gemini 3.1 Flash TTS in long-form content and dual-speaker screenplay control. In blind human preference evaluations on Voice Arena, the models ranked highly in several languages, including Japanese, Brazilian Portuguese, Vietnamese, Modern Standard Arabic, Mexican Spanish, and Hindi.
The models are rolling out starting today. Gemini 3.8 Flash TTS is available in the Gemini API and Google AI Studio for developers, with enterprise availability coming soon via API in Gemini Enterprise, and is available to everyone in Gemini Notebook. Gemini 3.8 Flash-Lite TTS is also rolling out today. Partners including Figma, HeyGen, Linguana, Wondercraft, 99.co, and Ollang are integrating the models, while platforms such as Agora, LiveKit, Pipecat, and Vercel support deployment.