Gemini 3.1 Flash TTS and the Gemini voice models
Google's Gemini line added native text-to-speech in 2025 as a preview and made it a model in its own right with 3.1 Flash TTS. It has the page here and reads the same four scripts as every voice model on this site.
Google DeepMind · facts checked
Which one to pick
Side by side, measured
| Model | Price | Seconds per reading | 4 scripts cost | Voices |
|---|---|---|---|---|
| Gemini 3.1 Flash TTS | $0.05 per 1,000 characters via fal | 13 to 19 | $0.0487 | Thirty named voices, Kore by default, which we used; no cloning |
Seconds and cost are from our own runs of the same 4 prompts through each model; open a model for every reading and the request behind it.
Every version
| Version | Released | What changed |
|---|---|---|
| Gemini 2.5 Flash Preview TTS | First Gemini TTS preview with 30 voices and multi-speaker. | |
| Gemini 3.1 Flash TTS gemini-3.1-flash-tts | Inline tags, plain-language style directions, 80-plus languages. |
Frequently asked questions
Is Gemini TTS free?
Not on the API; the free tier excludes the TTS models. fal charges per character.