Gemini 3.1 Flash TTS
AudioNot available
Gemini 3.1 Flash text-to-speech. Fast, natural-sounding voice synthesis.
- Type
- Text to Audio
- Billed
- per 1K chars
- Provider
Pricing
/ 1K charsPrice$0.04 / 1K chars
Supported parameters
modelSettings- Promptprompt
- Voicevoice
Code examples
POST /v1/generationsGenerations are async — the request returns immediately with an id; poll for the result.
python
import requests
response = requests.post(
"https://api.modelstack.cc/v1/generations",
headers={"Authorization": "Bearer sk_YOUR_API_KEY"},
json={
"type": "TEXT_TO_AUDIO",
"prompt": "A serene mountain landscape at sunset",
"model": "google/gemini-tts-3-1-flash",
"modelSettings": {
"voice": "Rachel"
}
},
)
generation_id = response.json()["data"]["id"]
# Poll for the result
result = requests.get(
f"https://api.modelstack.cc/v1/generations/{generation_id}",
headers={"Authorization": "Bearer sk_YOUR_API_KEY"},
).json()
print(result["data"]["status"])Related models
More from Google
Frequently asked questions
How is Gemini 3.1 Flash TTS billed on ModelStack?expand_more
Gemini 3.1 Flash TTS (Text to Audio) is billed at a flat, prepaid rate of $0.04 / 1K chars — generation pricing has no tier-based discounts. Final request costs are available in the console.
Which parameters does Gemini 3.1 Flash TTS support?expand_more
Gemini 3.1 Flash TTS supports: Prompt, Voice.
How can I generate with Gemini 3.1 Flash TTS?expand_more
Use the Generate composer in your dashboard, or call the API directly with model `google/gemini-tts-3-1-flash` and type `TEXT_TO_AUDIO` — see the code example above.