Implementation:Openai Openai node Speech Create

Knowledge Sources	openai-node OpenAI TTS API
Domains	Audio, Speech_Synthesis
Last Updated	2026-02-15 00:00 GMT

Overview

Concrete tool for generating speech audio from text provided by the openai-node SDK.

Description

The Speech.create() method sends a POST to /audio/speech with text, model, and voice parameters. It returns a raw Response object containing binary audio data. The caller accesses the audio via .body (ReadableStream), .arrayBuffer(), or .blob().

Usage

Use this method to generate audio from text. Write the response body to a file or stream it to an audio player.

Code Reference

Source Location

• Repository: openai-node
• File: src/resources/audio/speech.ts
• Lines: L24-31 (create method), L36-91 (SpeechCreateParams)

Signature

class Speech extends APIResource {
  create(
    body: SpeechCreateParams,
    options?: RequestOptions,
  ): APIPromise<Response>;
}

interface SpeechCreateParams {
  input: string;                    // Text to synthesize (max 4096 chars)
  model: SpeechModel;              // 'tts-1' | 'tts-1-hd' | 'gpt-4o-mini-tts'
  voice: string;                    // 'alloy' | 'ash' | 'coral' | 'echo' | 'fable' | 'onyx' | 'nova' | 'shimmer' | 'sage' | 'ballad' | 'verse'
  response_format?: string;        // 'mp3' | 'opus' | 'aac' | 'flac' | 'wav' | 'pcm'
  speed?: number;                   // 0.25 to 4.0
  instructions?: string;           // Voice style instructions (gpt-4o-mini-tts only)
}

Import

import OpenAI from 'openai';
// Access via: client.audio.speech.create(...)

I/O Contract

Inputs

Name	Type	Required	Description
input	string	Yes	Text to synthesize (max 4096 characters)
model	SpeechModel	Yes	TTS model ('tts-1', 'tts-1-hd', 'gpt-4o-mini-tts')
voice	string	Yes	Voice ID ('alloy', 'echo', 'nova', etc.)
response_format	string	No (default 'mp3')	Output format
speed	number	No (default 1.0)	Playback speed (0.25-4.0)
instructions	string	No	Style instructions for gpt-4o-mini-tts

Outputs

Name	Type	Description
response	Response	Raw HTTP Response with binary audio data in body

Usage Examples

Generate and Save MP3

import OpenAI from 'openai';
import fs from 'fs';

const client = new OpenAI();

const response = await client.audio.speech.create({
  model: 'tts-1',
  voice: 'alloy',
  input: 'Hello! Welcome to our application.',
});

const buffer = Buffer.from(await response.arrayBuffer());
fs.writeFileSync('output.mp3', buffer);

Stream Audio

const response = await client.audio.speech.create({
  model: 'tts-1-hd',
  voice: 'nova',
  input: 'This is high-quality speech synthesis.',
  response_format: 'opus',
  speed: 1.2,
});

// Stream to file
const stream = response.body;
const fileStream = fs.createWriteStream('output.opus');
// Pipe the readable stream to the file

Related Pages

Implements Principle

• Principle:Openai_Openai_node_Text_To_Speech

Requires Environment

• Environment:Openai_Openai_node_Node_20_Runtime