Name: Gemini 3.8 text-to-speech models
Rating: 4.5 (2 reviews)

Generate custom character voices and direct scene dialogue across Google AI Studio, Gemini API, Gemini Enterprise, Gemini Notebook, and Google Vids.

tested this directly in AI Studio rather than just reading the launch post. zero setup since I already had a Google account logged in, went straight from the playground to generating a speech clip. gave it a line of dialogue with a hard tone shift in the middle (calm to panicked) plus a couple of vocal-burst tags like <gasp>, and it generated a 9-second clip in a few seconds with no fiddling. the tag system (style, expression, per-speaker settings) is more control than I expected from something this fast, and the dual-speaker screenplay mode is a real differentiator versus single-voice TTS APIs where you have to stitch turns together yourself.

the model card mentions rate limits but doesn't say what happens to a request that gets throttled mid-generation, no visible retry-or-fail indicator in the playground. also there's no obvious way to preview how a tag like <gasp> will land before you spend a generation on it, would help to have a quick tag reference inline instead of just "type '<' for tags."

looked at ElevenLabs for the same use case. ElevenLabs still has the edge on raw voice cloning and library size, but Gemini's advantage is that scene direction and multi-speaker dialogue are native to the API instead of something you build on top yourself.

Gemini powers parts of the cup understanding and gives Tellwe its voice.

Gemini 3.8 text-to-speech models

Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS

Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS

Gemini 3.8 text-to-speech models Reviews

The community submitted 2 reviews to tell us what they like about Gemini 3.8 text-to-speech models, what Gemini 3.8 text-to-speech models can do better, and more.

What's great

What needs improvement

vs Alternatives

Alternatives Considered