Google DeepMind Launches Gemini 3.8 Flash TTS Voice Models

Google DeepMind released Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS on September 23, 2026, available immediately via the Gemini API and Google AI Studio, with enterprise availability listed as coming soon. Flash TTS supports generating new voices from natural language prompts, replicating a voice from a 30-second sample, and accessing over 2,000 production-ready voices across more than 100 languages. Flash-Lite TTS targets high-volume, cost-efficient use cases such as dubbing and voice agents, with access to user-created voice styles and the production-ready library. Google DeepMind said Flash TTS ranked first overall on Hume AI's Voice Design Benchmark with a score of 71.4 and led in accent modeling with a score of 60.8, with both models taking the top two spots on Hume AI's Overall Quality Index. Safety measures include consent verification for voice replication, SynthID watermarking on all generated audio, and C2PA credentials. Developer Simon Willison built a bring-your-own-key playground using the Gemini API and reported that generating 1 minute 18 seconds of audio took approximately 20 seconds and cost 2.74 cents using Flash TTS. The API supports multi-character conversations where each character can carry distinct voices and style instructions.