Google DeepMind (Gemini) / gemini-3-1-flash-tts-preview
Gemini 3.1 Flash TTS Preview stands out for Streaming Gemini speech for low-latency playback and Fine-grained style and expression controls. It is best suited to interactive voice assistants and expressive short-form narration.
Context
8K
token
Input
$0.90
/ 1M tokens
Output
$18.00
/ 1M tokens
Quality
—
No score
Overview
Gemini 3.1 Flash TTS Preview stands out for Streaming Gemini speech for low-latency playback and Fine-grained style and expression controls. It is best suited to interactive voice assistants and expressive short-form narration.
Audio output
Can produce audio output, commonly used for speech or voice experiences.
Streaming
Supports streamed responses for chat, assistants, and interfaces that need visible incremental output.
Model maker
Google DeepMind (Gemini)
Called through SeaLink's unified account, balance, and OpenAI-compatible API.
Protocol
Audio API
Base URL: https://api.sealink.io/v1
Pricing
The final charge follows generated usage and the applicable selector, such as resolution, duration, input type, or provider unit.
API
model
gemini-3-1-flash-tts-previewbase_url
https://api.sealink.io/v1Auth
Bearer $SEALINK_API_KEYcurl https://api.sealink.io/v1/audio/speech \-H "Authorization: Bearer $SEALINK_API_KEY" \-H "Content-Type: application/json" \-d '{"model": "gemini-3-1-flash-tts-preview","input": "Hello, welcome to SeaLink.","voice": "Kore","response_format": "wav"}' --output speech.wav
from openai import OpenAIclient = OpenAI(base_url="https://api.sealink.io/v1", api_key="<your-sealink-key>")resp = client.audio.speech.create(model="gemini-3-1-flash-tts-preview",input="Hello, welcome to SeaLink.",voice="Kore",response_format="wav",)resp.stream_to_file("speech.wav")
import OpenAI from "openai";import fs from "fs";const client = new OpenAI({baseURL: "https://api.sealink.io/v1",apiKey: process.env.SEALINK_API_KEY,});const resp = await client.audio.speech.create({model: "gemini-3-1-flash-tts-preview",input: "Hello, welcome to SeaLink.",voice: "Kore",response_format: "wav",});const buffer = Buffer.from(await resp.arrayBuffer());fs.writeFileSync("speech.wav", buffer);