Turn a script into speech with Gemini 3.1 Flash TTS and steer delivery with instructions. Price is based on script length. Pay per use.
Make your budget tangible
All your selected credit on Gemini 3.1 Flash TTS.
$0.18 per reference run
1,000 input characters; default voice settings. Settings and source media affect the estimate. Review the studio price before creating.The practical differences
Supported controls in Supermodels, rather than measured quality rankings. Prices use each model’s stated reference workload.
| Capabilities | Gemini 3.1 Flash TTSGoogle | Eleven Turbo v2.5ElevenLabs | Gemini 3.8 Flash TTSGoogle |
|---|---|---|---|
| Reference price | $0.181,000 input characters; default voice settings | $0.081,000 input characters; default voice settings | $0.051,000 input characters; estimated audio at 12 characters/second and 32 audio tokens/second |
| Voice selection | Supported | Supported | Supported |
| Language control | Supported | Supported | Not available |
| Speed control | Not available | Supported | Not available |
| Two-speaker dialogue | Not available | Not available | Supported |
| Language detection | Not available | Not available | Automatic |
| Output format | Not available | Not available | MP3 · WAV |
From reading to making
Prepare your inputs and inspect the estimate. Generation requires an account and wallet credit.
You're finally here, and I've been waiting longer than you can imagine. You found the old key in the attic, didn't you? I know which door it opens, but before you turn it, there's something you need to understand.
English
High quality, low latency text to speech in 32 languages