[Google DeepMind Releases Gemini 3.8 Flash TTS and Flash-Lite TTS Voice Models] According to DeepTech TechFlow, on September 24, Google DeepMind released two text-to-speech models, Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS. According to the official introduction, the new models support designing voices from scratch using natural language prompts, replicating voices with a 30-second sample, providing line-by-line performance guidance, generating long-form audio, and orchestrating dual-speaker scenarios, covering over 100 languages.