Gemini 3.1 Flash TTS, Text to Speech, Audio Output
Overview
Gemini 3.1 Flash TTS, Text to Speech, Audio Output is a music-generation model from Google, available through the AI Generate API. You call it with the same Bearer token and the same create-task request as every other model in the catalog, so no provider SDK is needed. Price: $19.6000 per million tokens, charged per use from your credit balance.
Use via API
curl https://aimarcusimage.eu/api/v1/jobs/createTask \
-H "Authorization: Bearer sk-aig-..." \
-H "Content-Type: application/json" \
-d '{
"model": "google-gemini-3-1-flash-tts-text-to-speech-audio-output",
"input": {
"prompt": "upbeat synthwave, driving bass"
}
}'
Async jobs (video, image, music) return a taskId. Poll /api/v1/jobs/recordInfo?taskId=... or pass a webhook URL to receive the result links.
Prompt examples
Pricing compare
| Provider | Price per million tokens | Notes |
|---|---|---|
| AI Generate | $19.6000 | This site. Pay as you go from $10, no subscription. |
| fal.ai | $20.0000 | fal.ai list price for the same model, for reference. |
| Directly from Google | varies | Separate account and billing with the provider. |
Related models
Suno, Generate Lyrics
Gemini 2.5 Pro TTS, Text to Speech, Audio Output
Elevenlabs Text to Speech, turbo 2.5
Sonilo Text to Music (≤60s)
Gemini 3.8 Flash TTS, Text to Speech, Audio Output
Suno, Vocal Separate
FAQ
How much does Gemini 3.1 Flash TTS, Text to Speech, Audio Output cost?+
$19.6000 per million tokens, charged from your credit balance. No monthly subscription and no minimum commitment. Top-ups start at $10 for 1,430 credits.
What kind of model is Gemini 3.1 Flash TTS, Text to Speech, Audio Output?+
Gemini 3.1 Flash TTS, Text to Speech, Audio Output is a music-generation model from Google, served through the AI Generate API.
How do I call Gemini 3.1 Flash TTS, Text to Speech, Audio Output from my code?+
Send an HTTPS POST with your Bearer token to our /api/v1/ endpoint. Every model uses the same create-task request, so no provider SDK is needed. The "Use via API" section above has a working curl example.
Can I use Gemini 3.1 Flash TTS, Text to Speech, Audio Output in production?+
Yes. The limit is 20 new requests per 10 seconds per API key, and status polling does not count against it. Each job returns a taskId, and you get the result by polling or through a webhook. Daily and monthly spend caps in the dashboard settings protect you from runaway usage.
What is the markup over the upstream price?+
We add 40% to the upstream price at the starting tier. When your spend over the last 30 days reaches $50, $200, $1,000 or $5,000, the markup drops to 30%, 22%, 15% or 10% automatically.
Ready to try Gemini 3.1 Flash TTS, Text to Speech, Audio Output?
Create an account and top up from $10 (1,430 credits). You pay only for what you run: $19.6000 per million tokens.