Back to all models

Gemini 2.5 Flash Preview TTS

Gemini 2.5 Flash text-to-speech model. Generates natural, controllable single-speaker audio from text via the /v1/audio/speech endpoint.

gemini-2.5-flash-preview-tts
STABLEGet StartedView uptime
8,000 context
Starting at $0.50/M input tokens
Starting at $10.00/M output tokens

Select Provider

All Providers for Gemini 2.5 Flash Preview TTS

LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.

Google AI Studio
Context: 8k
Input
$0.5
/M tokens
Cached
—
/M tokens
Output
$10
/M tokens
Get Started