On September 23, local time, Google announced the launch of two text-to-speech models, Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS. The former is designed for sound and character, supports the creation of customized sounds through natural language, and controls tone, speech speed, accent, etc. sentence by sentence; the latter is aimed at large-scale audio generation and dubbing scenarios. According to Google, the two models support more than 100 languages and dialects, and provide more than 2,000 directly usable sounds. Flash TTS also supports copying sounds based on 30 seconds of audio samples.

On September 23, local time, Google announced the launch of two text-to-speech models, Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS. The former is designed for sound and character, supports the creation of customized sounds through natural language, and controls tone, speech speed, accent, etc. sentence by sentence; the latter is aimed at large-scale audio generation and dubbing scenarios. According to Google, the two models support more than 100 languages and dialects, and provide more than 2,000 directly usable sounds. Flash TTS also supports copying sounds based on 30 seconds of audio samples.