Skip to main content
POST
/
audio-to-text
音声をテキストに変換
curl --request POST \
  --url https://{api_base_url}/audio-to-text \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form file='@example-file' \
  --form 'user=<string>'
import requests

url = "https://{api_base_url}/audio-to-text"

files = { "file": ("example-file", open("example-file", "rb")) }
payload = { "user": "<string>" }
headers = {"Authorization": "Bearer <token>"}

response = requests.post(url, data=payload, files=files, headers=headers)

print(response.text)
const form = new FormData();
form.append('file', '<string>');
form.append('user', '<string>');

const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};

options.body = form;

fetch('https://{api_base_url}/audio-to-text', 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_base_url}/audio-to-text",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"user\"\r\n\r\n<string>\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: multipart/form-data"
  ],
]);

$response = curl_exec($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_base_url}/audio-to-text"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"user\"\r\n\r\n<string>\r\n-----011000010111000001101001--")

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

	req.Header.Add("Authorization", "Bearer <token>")

	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_base_url}/audio-to-text")
  .header("Authorization", "Bearer <token>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"user\"\r\n\r\n<string>\r\n-----011000010111000001101001--")
  .asString();
require 'uri'
require 'net/http'

url = URI("https://{api_base_url}/audio-to-text")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"user\"\r\n\r\n<string>\r\n-----011000010111000001101001--"

response = http.request(request)
puts response.read_body
{
  "text": "Hello, I would like to know more about the iPhone 13 Pro Max."
}

Authorizations

​
Authorization
string
header
required

API Key 認証です。すべての API リクエストにおいて、Authorization HTTP ヘッダーに Bearer プレフィックスを付けた API Key を含めてください。例：Authorization: Bearer {API_KEY}。API Key はサーバーサイドに保存し、クライアントサイドで共有・保存しないことを強く推奨します。API Key の漏洩は深刻な結果につながる可能性があります。API Key が欠落または無効な場合、HTTP 401 とエラーコード unauthorized が返されます。

Body

multipart/form-data

音声からテキストへの変換のリクエストボディ。

​
file
file
required

音声ファイルです。MIME タイプで検証され、audio/mp3、audio/m4a、audio/wav、audio/amr、audio/mpga のいずれかである必要があります。上限：30 MB。

​
user
string

ユーザー識別子。

Response

音声からテキストへの変換に成功しました。

​
text
string

音声認識からの出力テキスト。

Last modified on July 9, 2026