gemini-3.1-flash-tts-preview
Preview Gemini 3.1 TTS model for low-latency, prompt-controllable single- and multi-speaker generation; supports inline audio tags such as [laughs].
01 Price
$1.00per 1M tokens
| Plan or mode | Price |
|---|---|
| text_input | $1.00 per 1M tokens |
| audio_output | $20.00 per 1M tokens |
US$1.00 per 1M text input tokens; US$20.00 per 1M audio output tokens (25 audio tokens per second). No free tier.
Pricing source, checked 2026-11-16
02 Languages
Not published.
03 Features 4 of 8 listed
- Emotion control
- Voice cloningnot listed
- Voice designnot listed
- SSMLnot listed
- Phoneme inputnot listed
- Speed / prosody control
- Style control
- Multi-speaker
"Not listed" means the provider's data doesn't mention it, not that the model lacks it.
04 Voices 30 compatible, browse all
-
No sample published
Achernar
Sample unavailable. The provider may have moved it.
female, american / English (US)
Achernar -
No sample published
Achird
Sample unavailable. The provider may have moved it.
male, american / English (US)
Achird -
No sample published
Algenib
Sample unavailable. The provider may have moved it.
male, american / English (US)
Algenib -
No sample published
Algieba
Sample unavailable. The provider may have moved it.
male, american / English (US)
Algieba -
No sample published
Alnilam
Sample unavailable. The provider may have moved it.
male, american / English (US)
Alnilam -
No sample published
Aoede
Sample unavailable. The provider may have moved it.
female, american / English (US)
Aoede
05 Get this record
curl https://voicedex.dev/v1/providers/google-cloud/models/gemini-3.1-flash-tts-preview
Free, no key needed. Use model id gemini-3.1-flash-tts-preview with Google Cloud's own API. API reference.