Gemini 3.1 Flash TTS Preview audio
google/gemini-3.1-flash-tts-preview · family gemini-flash · in: text → out: audio · price provider-declared (via models.dev). Capabilities: reasoning text.
$5.75
Blended $/1M (3:1)
$1
Input $/1M
$20
Output $/1M
$21.00
1M in + 1M out
—
Cache read $/1M
#6664 of 7,708
Cheapest rank
- Provider
- Google (
google) - Kind
- audio (outputs audio)
- Context
- 8,192 tokens
- Max output
- 16,384 tokens
- Capabilities
- reasoning text
Same model, other providers
“Gemini 3.1 Flash TTS Preview” is offered by 2 providers — cheapest-effective first. This one (Google) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Google (this) | $1 | $20 | $5.75 | 8k |
| Kenari | — | — | — | 8k |
Call it
jishie indexes & prices models; it does not proxy inference.
Audio generation — call Google’s audio API with model id gemini-3.1-flash-tts-preview. Endpoints vary by provider; see their docs.
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):