Text-to-Speech

Convert text to audio.

Try It

POST/v1/audio/speechhttps://api-platform.ope.ai

Authentication

Uses Bearer Token authentication.

• Header: Authorization: Bearer <token>
• Example: Authorization: Bearer sk-xxxxxx

Request body (application/json)

Field	Type	Required	Description	Default / Range
model	string	Yes	Model ID	-
text	string	Yes	Text to convert	Length <= 4096
voice	string	Yes	Voice	Each model supports different voices, please check specific model documentation
response_format	string	No	Audio format	Default "mp3"; "mp3" | "opus" | "aac" | "flac" | "wav" | "pcm"
speed	number	No	Speed	Default 1; Range 0.1~4

Request examples

The domain below is an example: https://api-platform.ope.ai.

cURL

curl -X POST "https://api-platform.ope.ai/v1/audio/speech" \
  -H "Authorization: Bearer $OPEAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "AudioLLM/Voice1.0",
    "text": "Supports multi-scenario customization for advertising voiceovers, tutorial narrations, and more",
    "voice": "James"
  }' --output speech.mp3

JavaScript

const url = "https://api-platform.ope.ai/v1/audio/speech";
const apiKey = process.env.OPEAI_API_KEY;

const res = await fetch(url, {
  method: "POST",
  headers: {
    Authorization: `Bearer ${apiKey}`,
    "Content-Type": "application/json",
    Accept: "audio/mpeg",
  },
  body: JSON.stringify({
    model: "AudioLLM/Voice1.0",
    text: "Supports multi-scenario customization for advertising voiceovers, tutorial narrations, and more",
    voice: "James",
  }),
});

const arrayBuffer = await res.arrayBuffer();
// In Node environment write file:
// import { writeFileSync } from "node:fs";
// writeFileSync("speech.mp3", Buffer.from(arrayBuffer));
console.log(res.status, arrayBuffer.byteLength);

Go

package main

import (
  "bytes"
  "io"
  "net/http"
  "os"
)

func main() {
  body := []byte(`{"model":"AudioLLM/Voice1.0","text":"Supports multi-scenario customization for advertising voiceovers, tutorial narrations, and more","voice":"James"}`)
  req, _ := http.NewRequest("POST", "https://api-platform.ope.ai/v1/audio/speech", bytes.NewBuffer(body))
  req.Header.Set("Authorization", "Bearer "+os.Getenv("OPEAI_API_KEY"))
  req.Header.Set("Content-Type", "application/json")
  req.Header.Set("Accept", "audio/mpeg")

  resp, err := http.DefaultClient.Do(req)
  if err != nil {
    panic(err)
  }
  defer resp.Body.Close()

  out, _ := os.Create("speech.mp3")
  defer out.Close()
  io.Copy(out, resp.Body)
}

Python

import os
import requests

resp = requests.post(
  "https://api-platform.ope.ai/v1/audio/speech",
  headers={
    "Authorization": f"Bearer {os.environ.get('OPEAI_API_KEY')}",
    "Content-Type": "application/json",
    "Accept": "audio/mpeg",
  },
  json={"model": "AudioLLM/Voice1.0", "text": "Supports multi-scenario customization for advertising voiceovers, tutorial narrations, and more", "voice": "James"},
  timeout=60,
)

with open("speech.mp3", "wb") as f:
  f.write(resp.content)

Java

import java.io.FileOutputStream;
import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;

public class Main {
  public static void main(String[] args) throws Exception {
    String apiKey = System.getenv("OPEAI_API_KEY");
    String url = "https://api-platform.ope.ai/v1/audio/speech";

    String json = """
      { "model": "AudioLLM/Voice1.0", "text": "Supports multi-scenario customization for advertising voiceovers, tutorial narrations, and more", "voice": "James" }
      """;

    HttpRequest request = HttpRequest.newBuilder()
      .uri(URI.create(url))
      .header("Authorization", "Bearer " + apiKey)
      .header("Content-Type", "application/json")
      .header("Accept", "audio/mpeg")
      .POST(HttpRequest.BodyPublishers.ofString(json))
      .build();

    HttpClient client = HttpClient.newHttpClient();
    HttpResponse<byte[]> response = client.send(request, HttpResponse.BodyHandlers.ofByteArray());
    try (FileOutputStream fos = new FileOutputStream("speech.mp3")) {
      fos.write(response.body());
    }
    System.out.println(response.statusCode());
  }
}

C#

using System;
using System.IO;
using System.Net.Http;
using System.Net.Http.Headers;
using System.Text;
using System.Threading.Tasks;

public class Program
{
  public static async Task Main()
  {
    var apiKey = Environment.GetEnvironmentVariable("OPEAI_API_KEY");
    var url = "https://api-platform.ope.ai/v1/audio/speech";

    var json = """
    { "model": "AudioLLM/Voice1.0", "text": "Supports multi-scenario customization for advertising voiceovers, tutorial narrations, and more", "voice": "James" }
    """;

    using var http = new HttpClient();
    http.DefaultRequestHeaders.Authorization = new AuthenticationHeaderValue("Bearer", apiKey);
    http.DefaultRequestHeaders.Accept.Add(new MediaTypeWithQualityHeaderValue("audio/mpeg"));
    var content = new StringContent(json, Encoding.UTF8, "application/json");

    var resp = await http.PostAsync(url, content);
    var bytes = await resp.Content.ReadAsByteArrayAsync();
    await File.WriteAllBytesAsync("speech.mp3", bytes);
    Console.WriteLine((int)resp.StatusCode);
  }
}

Response example

• 200: audio/mpeg (binary audio data, saved as speech.mp3 in examples)