Gemini TTS AI Model Series
Gemini TTS — Google's native speech model that turns text (and a style prompt) into expressive, multi-speaker audio, in Flash and Pro flavors.
All Gemini TTS Models
google/gemini-3.8-flash-lite-tts
Google's fast text-to-speech model for voice agents, read-aloud, and high-volume narration. It covers 101 languages, with single-speaker speech or a two-speaker scene, at lower latency than Gemini 3.8 Flash TTS.
google/gemini-3.8-flash-tts
Google's studio text-to-speech model for audiobooks, long narration, and expressive two-speaker scenes. It covers 130 languages and follows turn-by-turn delivery, including a designed or library voice.
google/gemini-3.1-flash-tts
Google's low-latency text-to-speech model for voiceovers, presenters, and two-person dialogue. It speaks with one of 30 preset voices and can follow a style direction for pace and emotion.
Explore More
Explore Text to Speech models and APIs on Modellix.
11 models
Explore Gemini ASR models and APIs on Modellix.
1 models
Explore MiniMax Speech models and APIs on Modellix.
3 models
Explore CosyVoice models and APIs on Modellix.
4 models
Explore Fun ASR models and APIs on Modellix.
1 models
Explore Grok Voice models and APIs on Modellix.
2 models
