Google launched Gemini 3.8 Flash TTS and Flash-Lite TTS, supporting over 100 languages and dialects and 2,000-plus voices.

Google (谷歌) announced Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, two text-to-speech models (文本转语音模型). The supplied report attributes support for more than 100 languages and dialects and more than 2,000 ready-to-use voices to Google.

Flash TTS targets voice and character design (声音和角色设计). It supports creating customized voices through natural-language instructions and controlling tone, speaking speed, and accent sentence by sentence (逐句控制语气、语速、口音等).

Flash-Lite TTS targets large-scale audio generation and dubbing (大规模音频生成和配音场景). Flash TTS additionally supports voice replication from a 30-second audio sample (“基于 30 秒音频样本复制声音”); the supplied report does not provide prices, latency measurements, or voice-consent requirements.