Gemini TTS API SDK for RunAPI

Gemini TTS API SDKs for JavaScript, Python, Ruby, Go, Java, and PHP on RunAPI, covering multi-speaker speech generation.

Gemini TTS on RunAPI turns ordered dialogue into speech with per-speaker voices, accents, styles, pacing, and optional voice profiles. The SDKs provide typed requests and a consistent create, get, and run lifecycle.

Install

npm install @runapi.ai/gemini-tts
pip install runapi-gemini-tts
gem install runapi-gemini-tts
go get github.com/runapi-ai/gemini-tts-sdk/go@latest

Gradle:

implementation("ai.runapi:runapi-gemini-tts:0.1.0")

The PHP package is published from the split Composer repository as runapi-ai/gemini-tts; see https://github.com/runapi-ai/gemini-tts-php.

JavaScript quick start

import { GeminiTtsClient } from '@runapi.ai/gemini-tts';

const client = new GeminiTtsClient();
const result = await client.textToSpeech.run({
  model: 'gemini-2.5-pro-tts',
  speakers: [{
    speaker_id: 'Speaker 1',
    voice_name: 'Fenrir',
    accent: 'British (RP)',
    style: 'Deadpan',
    pace: 'Natural',
  }],
  dialogue_turns: [{ speaker_id: 'Speaker 1', text: 'Welcome.' }],
});

console.log(result.audios[0].url);

Use create() to submit without waiting, get(id) to fetch task status, or run() to submit and poll until completion.

Links

• Model page: https://runapi.ai/models/gemini-tts
• Gemini 2.5 Pro TTS: https://runapi.ai/models/gemini-tts/gemini-2.5-pro-tts
• Gemini 3.1 Flash TTS: https://runapi.ai/models/gemini-tts/gemini-3.1-flash-tts
• API reference: https://runapi.ai/docs#gemini-tts
• Provider comparison: https://runapi.ai/providers/google
• Full catalog: https://runapi.ai/models

RunAPI-generated file URLs are temporary. Store generated audio in your own durable storage.

Licensed under the Apache License, Version 2.0.