All models

Gemini 3.1 Flash TTS

google/gemini-3.1-flash-tts
Google

Quick start

# Inspect the price — a plain request returns the 402 challenge:
curl -i https://api.glianalabs.com/v1/infer \
  -H "content-type: application/json" \
  -d '{
    "model": "google/gemini-3.1-flash-tts",
    "text": "<text to speak>"
  }'

# Pay + run in one step with the mppx CLI (create a wallet: npx mppx account create):
npx mppx https://api.glianalabs.com/v1/infer \
  -J '{"model": "google/gemini-3.1-flash-tts", "text": "<text to speak>"}'

Examples

Parameters

Input
text string required

The text to convert to speech. Maximum 10,000 characters.

maxOutputTokens integer optional

Maximum number of tokens to generate

stopSequences array optional

Sequences where the model will stop generating further tokens

temperature number optional

Controls randomness in generation (0-2)

topK integer optional

Only sample from the top K tokens. Smaller K = more focused, larger K = more diverse

topP number optional

Nucleus sampling threshold (0-1). Tokens with cumulative probability up to topP are considered

voice string optional

The voice to use for speech synthesis

Output
audio: Base64-encoded audio data (WAV format)