gemini-3.8-flash-tts
A text-to-speech model released by Google, supporting a library of over 2,000 voices, multi-speaker dialogue generation, and voice cloning, with high-performance speech synthesis capabilities.
Timeline (last 90 days)
Google has released two text-to-speech models, gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts.
gemini-3.8-flash-tts offers stronger performance, while gemini-3.8-flash-lite-tts offers lower cost.
Both models come with a built-in voice library of over 2,000 voices, covering multiple languages and timbres.
Gemini 3.8 TTS's native multi-speaker support enables the model to perceive the entire conversation context within a single inference pass, eliminating the need for post-processing concatenation.
Generating 1 minute and 18 seconds of audio using Gemini 3.8 Flash TTS took approximately 20 seconds and cost 2.74 cents.
All Facts (5)
gemini-3.8-flash-tts offers stronger performance, while gemini-3.8-flash-lite-tts offers lower cost.
50%UnverifiedBoth models come with a built-in voice library of over 2,000 voices, covering multiple languages and timbres.
50%UnverifiedGemini 3.8 TTS's native multi-speaker support enables the model to perceive the entire conversation context within a single inference pass, eliminating the need for post-processing concatenation.
50%UnverifiedGenerating 1 minute and 18 seconds of audio using Gemini 3.8 Flash TTS took approximately 20 seconds and cost 2.74 cents.
50%UnverifiedGoogle has released two text-to-speech models, gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts.
60%