Google releases Gemini 3.8 text-to-speech models

Google released Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, two text-to-speech models designed for expressive audio generation. Both are available through the Gemini API and Google AI Studio, with integrations also reaching Google products including Notebook and Vids.

Flash TTS is aimed at creative direction and character design, including custom voices, line-by-line acting cues, pacing and dialect changes. Flash-Lite is tuned for higher-volume uses such as dubbing and voice agents. Google says generated audio includes watermarking and that voice replication uses consent checks.

The split gives developers separate quality and throughput options rather than a single speech model for every workload. Voice quality still depends on language, prompt and use case, so benchmark rankings do not establish uniform performance across every production setting.