Google DeepMind Releases Gemini 3.8 Flash TTS and Flash-Lite TTS Speech Models

Google DeepMind has released two text-to-speech models, Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS. According to the official description, the new models support designing voices from scratch using natural language prompts or cloning them with a 30-second sample. They also provide line-by-line performance guidance, long-form audio generation, and dual-speaker scenario orchestration, covering more than 100 languages.