跳转到主要内容
POST
/
audio-to-text
cURL
curl --request POST \
  --url 'https://{api_base_url}/audio-to-text' \
  --header 'Authorization: Bearer {api_key}' \
  --form 'file=@meeting-question.mp3' \
  --form 'user={user}'
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; boundary=---011000010111000001101001"
],
]);

$response = curl_exec($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>")
req.Header.Add("Content-Type", "multipart/form-data; boundary=---011000010111000001101001")

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>")
.header("Content-Type", "multipart/form-data; boundary=---011000010111000001101001")
.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["Content-Type"] = 'multipart/form-data; boundary=---011000010111000001101001'
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."
}

授权

Authorization
string
header
必填

每个请求都通过 API Key 认证:Authorization: Bearer {API_KEY}。应用接口使用应用 API Key,知识库接口使用知识库 API Key(快速开始)。

API Key 应保存在服务端,切勿嵌入客户端代码。缺失或无效的 Key 会返回 HTTP 401unauthorized)。

请求体

multipart/form-data

语音转文字的请求体。

file
file
必填

要转写的音频文件。接受的 MIME 类型:audio/mp3audio/m4aaudio/wavaudio/amraudio/mpga。其他类型(包括常见的 audio/mpeg)会返回 unsupported_audio_type 错误。最大 30 MB

user
string

终端用户标识,由你的应用定义,需在应用内唯一。参见 终端用户身份

响应

语音转文字成功。

text
string

语音识别输出的文字。