Gemini 3.1 Flash TTS Preview

Google

google/gemini-3.1-flash-tts-previewClosed API

Low-latency speech generation with steerable prompts and expressive audio tags

Benchmark Pricing$1.00 / 1M in$20.00 / 1M out

Context: 8,192 tokens•Max Output: 16,384 tokens•Knowledge: 2025-01•Released: 2026-04-15

TECHNICAL SPECIFICATIONS

Context Window8,1928.2K tokens

Max Output16,38416.4K tokens

LicenseProprietaryCloud API only

Input Modalities

Text

Function / Tool CallingNot Supported

Structured OutputsPrompt Based

MODEL CONTEXT PROTOCOL (MCP) READINESS

⚠ Gemini 3.1 Flash TTS Preview does not natively advertise tool-calling capabilities. When connecting to MCP servers, function calling must be handled via structured prompt injection.

MCP Context Window Recommendations

With a context capacity of 8,192 tokens, this model can handle compact tool sets. Consider keeping MCP server tool manifests minimal to preserve headroom.

API CALL INVOCATION EXAMPLE

// Example: Calling Gemini 3.1 Flash TTS Preview via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.GOOGLE_API_KEY,
});

const response = await client.chat.completions.create({
  model: "google/gemini-3.1-flash-tts-preview",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);