Gemini 3.8 Flash TTS

Overview. Gemini 3.8 Flash TTS is a dedicated text-to-speech model developed by Google that converts text prompts directly into synthetic speech. Built for high-throughput media and voice interfaces, it outputs audio across more than 130 languages. Developers reach for it to produce voice outputs with granular direction over vocal delivery and persona styling.

Key strengths. The model provides expressive speech synthesis across over 130 languages, supporting turn-level style direction, voice design personas, and voice replication. Backed by an 8,192-token input limit and a 16,384-token output ceiling, it can sustain extended spoken passages as well as rapid interactive dialogue.

When to use it. Use Gemini 3.8 Flash TTS when building voice agents, multilingual narration pipelines, or spoken alert systems requiring interactive latency. It is selected via the Smart Router for simple speech synthesis tasks that need expressive vocal control rather than reasoning or text comprehension.

Limitations. Gemini 3.8 Flash TTS functions strictly as an audio synthesis engine and does not perform text generation, reasoning, or structured tool calling. It accepts text input only, lacking support for multimodal visual context or audio understanding.

Sovereignty note. Gemini 3.8 Flash TTS is a proprietary model developed by Google in the United States and subject to US jurisdiction, including the CLOUD Act. Customer data handling and data residency follow Google API commercial terms.