Gemini 3.1 Flash TTS Preview

Gemini 3.1 Flash text-to-speech model. Generates low-latency, prompt-steerable audio from text via the /v1/audio/speech endpoint.

google-vertex/gemini-3.1-flash-tts-preview
STABLEGet Started
No ratings yetSign in to rate

Google Vertex AI Pricing for Gemini 3.1 Flash TTS Preview

View detailed pricing and capabilities for this provider.

Context: 8k
Input
$1
/M tokens
Cache Read
/M tokens
Output
$20
/M tokens
Audio Output
$20
/M tokens
Get Started