Create speech with an OpenAI-compatible API

Create speech from an OpenAI Audio Speech API-compatible request and return WAV audio. voice accepts a VOICEVOX style ID, an AI SDK voice alias, or an OpenAI voice name. speed is applied to VOICEVOX speedScale. model, instructions, response_format, and stream_format are accepted for compatibility, but the Laravel implementation currently always returns WAV audio.

Laravel Implementation Status: ✅ Fully supported by Core (fallback implemented)

POST /v1/audio/speech

Create speech with an OpenAI-compatible API

cURL

curl --request POST \
  --url https://api.example.com/v1/audio/speech \
  --header 'Content-Type: application/json' \
  --data '
{
  "input": "<string>",
  "voice": "<string>",
  "model": "<string>",
  "instructions": "<string>",
  "response_format": "<string>",
  "speed": 1,
  "stream_format": "<string>"
}
'

import requests

url = "https://api.example.com/v1/audio/speech"

payload = {
    "input": "<string>",
    "voice": "<string>",
    "model": "<string>",
    "instructions": "<string>",
    "response_format": "<string>",
    "speed": 1,
    "stream_format": "<string>"
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    input: '<string>',
    voice: '<string>',
    model: '<string>',
    instructions: '<string>',
    response_format: '<string>',
    speed: 1,
    stream_format: '<string>'
  })
};

fetch('https://api.example.com/v1/audio/speech', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.example.com/v1/audio/speech",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'input' => '<string>',
    'voice' => '<string>',
    'model' => '<string>',
    'instructions' => '<string>',
    'response_format' => '<string>',
    'speed' => 1,
    'stream_format' => '<string>'
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.example.com/v1/audio/speech"

	payload := strings.NewReader("{\n  \"input\": \"<string>\",\n  \"voice\": \"<string>\",\n  \"model\": \"<string>\",\n  \"instructions\": \"<string>\",\n  \"response_format\": \"<string>\",\n  \"speed\": 1,\n  \"stream_format\": \"<string>\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.example.com/v1/audio/speech")
  .header("Content-Type", "application/json")
  .body("{\n  \"input\": \"<string>\",\n  \"voice\": \"<string>\",\n  \"model\": \"<string>\",\n  \"instructions\": \"<string>\",\n  \"response_format\": \"<string>\",\n  \"speed\": 1,\n  \"stream_format\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.example.com/v1/audio/speech")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n  \"input\": \"<string>\",\n  \"voice\": \"<string>\",\n  \"model\": \"<string>\",\n  \"instructions\": \"<string>\",\n  \"response_format\": \"<string>\",\n  \"speed\": 1,\n  \"stream_format\": \"<string>\"\n}"

response = http.request(request)
puts response.read_body

200

"<string>"

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

본문

application/json

input · string · 필수

Text to synthesize

Maximum string length: 4096

voice · string integer Voice · object · 필수

VOICEVOX style ID, AI SDK voice alias, or OpenAI voice name

model · string

OpenAI-compatible model name. Accepted for compatibility in the Laravel implementation.

instructions · string

OpenAI-compatible parameter. Currently unused by the Laravel implementation.

Maximum string length: 4096

response_format · string

OpenAI-compatible parameter. The Laravel implementation currently always returns WAV audio.

speed · number · 기본값: 1

Speech speed applied to VOICEVOX speedScale

필수 범위: 0.25 <= x <= 4

stream_format · string

OpenAI-compatible parameter. Currently unused by the Laravel implementation.

응답

200

audio/wav

Successful Response

The response is of type file.