AiBox

Whisper-1 音频转录

  • 支持 99 种语言的语音识别

  • 多种输出格式：json、text、srt、vtt 等

  • 最大文件大小 25 MB

    curl --request POST \
  --url https://aiboxapi.com/v1/audio/transcriptions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form 'file=@/path/to/audio.mp3' \
  --form 'model=whisper-1' \
  --form 'language=zh' \
  --form 'response_format=json'

    import requests

url = "https://aiboxapi.com/v1/audio/transcriptions"

files = {
    "file": open("/path/to/audio.mp3", "rb")
}

data = {
    "model": "whisper-1",
    "language": "zh",
    "response_format": "json"
}

headers = {
    "Authorization": "Bearer <token>"
}

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

print(response.json())

    const url = "https://aiboxapi.com/v1/audio/transcriptions";

const formData = new FormData();
formData.append("file", audioFile);
formData.append("model", "whisper-1");
formData.append("language", "zh");
formData.append("response_format", "json");

const headers = {
  "Authorization": "Bearer <token>"
};

fetch(url, {
  method: "POST",
  headers: headers,
  body: formData
})
  .then(response => response.json())
  .then(data => console.log(data))
  .catch(error => console.error('Error:', error));

    package main

import (
    "bytes"
    "fmt"
    "io"
    "mime/multipart"
    "net/http"
    "os"
)

func main() {
    url := "https://aiboxapi.com/v1/audio/transcriptions"

    file, _ := os.Open("/path/to/audio.mp3")
    defer file.Close()

    body := &bytes.Buffer{}
    writer := multipart.NewWriter(body)
    
    part, _ := writer.CreateFormFile("file", "audio.mp3")
    io.Copy(part, file)
    
    writer.WriteField("model", "whisper-1")
    writer.WriteField("language", "zh")
    writer.WriteField("response_format", "json")
    writer.Close()

    req, _ := http.NewRequest("POST", url, body)
    req.Header.Set("Authorization", "Bearer <token>")
    req.Header.Set("Content-Type", writer.FormDataContentType())

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

    responseBody, _ := io.ReadAll(resp.Body)
    fmt.Println(string(responseBody))
}

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

public class Main {
    public static void main(String[] args) throws Exception {
        String url = "https://aiboxapi.com/v1/audio/transcriptions";
        
        File audioFile = new File("/path/to/audio.mp3");
        
        // 使用 Apache HttpClient 或 OkHttp 库来发送 multipart/form-data 请求
    }
}

    <?php

$url = "https://aiboxapi.com/v1/audio/transcriptions";

$file = new CURLFile('/path/to/audio.mp3', 'audio/mpeg', 'audio.mp3');

$data = [
    "file" => $file,
    "model" => "whisper-1",
    "language" => "zh",
    "response_format" => "json"
];

$ch = curl_init($url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, $data);
curl_setopt($ch, CURLOPT_HTTPHEADER, [
    "Authorization: Bearer <token>"
]);

$response = curl_exec($ch);
curl_close($ch);

echo $response;
?>

    require 'net/http'
require 'uri'

url = URI("https://aiboxapi.com/v1/audio/transcriptions")

File.open('/path/to/audio.mp3', 'rb') do |file|
  request = Net::HTTP::Post.new(url)
  request["Authorization"] = "Bearer <token>"
  
  form_data = [
    ['file', file, { filename: 'audio.mp3', content_type: 'audio/mpeg' }],
    ['model', 'whisper-1'],
    ['language', 'zh'],
    ['response_format', 'json']
  ]
  
  request.set_form form_data, 'multipart/form-data'
  
  http = Net::HTTP.new(url.host, url.port)
  http.use_ssl = true
  
  response = http.request(request)
  puts response.body
end

    import Foundation

let url = URL(string: "https://aiboxapi.com/v1/audio/transcriptions")!

var request = URLRequest(url: url)
request.httpMethod = "POST"
request.setValue("Bearer <token>", forHTTPHeaderField: "Authorization")

let boundary = "Boundary-\(UUID().uuidString)"
request.setValue("multipart/form-data; boundary=\(boundary)", forHTTPHeaderField: "Content-Type")

var body = Data()

// Add file
let fileURL = URL(fileURLWithPath: "/path/to/audio.mp3")
if let fileData = try? Data(contentsOf: fileURL) {
    body.append("--\(boundary)\r\n".data(using: .utf8)!)
    body.append("Content-Disposition: form-data; name=\"file\"; filename=\"audio.mp3\"\r\n".data(using: .utf8)!)
    body.append("Content-Type: audio/mpeg\r\n\r\n".data(using: .utf8)!)
    body.append(fileData)
    body.append("\r\n".data(using: .utf8)!)
}

// Add other fields
let fields = ["model": "whisper-1", "language": "zh", "response_format": "json"]
for (key, value) in fields {
    body.append("--\(boundary)\r\n".data(using: .utf8)!)
    body.append("Content-Disposition: form-data; name=\"\(key)\"\r\n\r\n".data(using: .utf8)!)
    body.append("\(value)\r\n".data(using: .utf8)!)
}

body.append("--\(boundary)--\r\n".data(using: .utf8)!)

request.httpBody = body

let task = URLSession.shared.dataTask(with: request) { data, response, error in
    if let error = error {
        print("Error: \(error)")
        return
    }
    
    if let data = data, let responseString = String(data: data, encoding: .utf8) {
        print(responseString)
    }
}

task.resume()

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

class Program
{
    static async Task Main(string[] args)
    {
        var url = "https://aiboxapi.com/v1/audio/transcriptions";

        using var client = new HttpClient();
        client.DefaultRequestHeaders.Add("Authorization", "Bearer <token>");

        using var form = new MultipartFormDataContent();
        
        var fileStream = File.OpenRead("/path/to/audio.mp3");
        form.Add(new StreamContent(fileStream), "file", "audio.mp3");
        form.Add(new StringContent("whisper-1"), "model");
        form.Add(new StringContent("zh"), "language");
        form.Add(new StringContent("json"), "response_format");

        var response = await client.PostAsync(url, form);
        var result = await response.Content.ReadAsStringAsync();

        Console.WriteLine(result);
    }
}

    #include <stdio.h>
#include <curl/curl.h>

int main(void) {
    CURL *curl;
    CURLcode res;
    struct curl_httppost *formpost = NULL;
    struct curl_httppost *lastptr = NULL;
    struct curl_slist *headers = NULL;

    curl_global_init(CURL_GLOBAL_ALL);

    curl_formadd(&formpost, &lastptr,
                 CURLFORM_COPYNAME, "file",
                 CURLFORM_FILE, "/path/to/audio.mp3",
                 CURLFORM_END);

    curl_formadd(&formpost, &lastptr,
                 CURLFORM_COPYNAME, "model",
                 CURLFORM_COPYCONTENTS, "whisper-1",
                 CURLFORM_END);

    curl_formadd(&formpost, &lastptr,
                 CURLFORM_COPYNAME, "language",
                 CURLFORM_COPYCONTENTS, "zh",
                 CURLFORM_END);

    curl_formadd(&formpost, &lastptr,
                 CURLFORM_COPYNAME, "response_format",
                 CURLFORM_COPYCONTENTS, "json",
                 CURLFORM_END);

    curl = curl_easy_init();
    headers = curl_slist_append(headers, "Authorization: Bearer <token>");

    if(curl) {
        curl_easy_setopt(curl, CURLOPT_URL, "https://aiboxapi.com/v1/audio/transcriptions");
        curl_easy_setopt(curl, CURLOPT_HTTPHEADER, headers);
        curl_easy_setopt(curl, CURLOPT_HTTPPOST, formpost);

        res = curl_easy_perform(curl);

        if(res != CURLE_OK) {
            fprintf(stderr, "curl_easy_perform() failed: %s\n",
                    curl_easy_strerror(res));
        }

        curl_easy_cleanup(curl);
        curl_formfree(formpost);
        curl_slist_free_all(headers);
    }

    curl_global_cleanup();
    return 0;
}

    #import <Foundation/Foundation.h>

int main(int argc, const char * argv[]) {
    @autoreleasepool {
        NSURL *url = [NSURL URLWithString:@"https://aiboxapi.com/v1/audio/transcriptions"];
        
        NSMutableURLRequest *request = [NSMutableURLRequest requestWithURL:url];
        [request setHTTPMethod:@"POST"];
        [request setValue:@"Bearer <token>" forHTTPHeaderField:@"Authorization"];
        
        NSString *boundary = @"Boundary-12345";
        NSString *contentType = [NSString stringWithFormat:@"multipart/form-data; boundary=%@", boundary];
        [request setValue:contentType forHTTPHeaderField:@"Content-Type"];
        
        NSMutableData *body = [NSMutableData data];
        
        // Add file
        NSData *fileData = [NSData dataWithContentsOfFile:@"/path/to/audio.mp3"];
        [body appendData:[[NSString stringWithFormat:@"--%@\r\n", boundary] dataUsingEncoding:NSUTF8StringEncoding]];
        [body appendData:[@"Content-Disposition: form-data; name=\"file\"; filename=\"audio.mp3\"\r\n" dataUsingEncoding:NSUTF8StringEncoding]];
        [body appendData:[@"Content-Type: audio/mpeg\r\n\r\n" dataUsingEncoding:NSUTF8StringEncoding]];
        [body appendData:fileData];
        [body appendData:[@"\r\n" dataUsingEncoding:NSUTF8StringEncoding]];
        
        // Add other fields
        NSDictionary *fields = @{@"model": @"whisper-1", @"language": @"zh", @"response_format": @"json"};
        for (NSString *key in fields) {
            [body appendData:[[NSString stringWithFormat:@"--%@\r\n", boundary] dataUsingEncoding:NSUTF8StringEncoding]];
            [body appendData:[[NSString stringWithFormat:@"Content-Disposition: form-data; name=\"%@\"\r\n\r\n", key] dataUsingEncoding:NSUTF8StringEncoding]];
            [body appendData:[[NSString stringWithFormat:@"%@\r\n", fields[key]] dataUsingEncoding:NSUTF8StringEncoding]];
        }
        
        [body appendData:[[NSString stringWithFormat:@"--%@--\r\n", boundary] dataUsingEncoding:NSUTF8StringEncoding]];
        [request setHTTPBody:body];
        
        NSURLSessionDataTask *task = [[NSURLSession sharedSession] 
            dataTaskWithRequest:request
            completionHandler:^(NSData *data, NSURLResponse *response, NSError *error) {
                if (error) {
                    NSLog(@"Error: %@", error);
                    return;
                }
                NSString *result = [[NSString alloc] initWithData:data encoding:NSUTF8StringEncoding];
                NSLog(@"%@", result);
            }];
        
        [task resume];
        [[NSRunLoop mainRunLoop] run];
    }
    return 0;
}

    (* Requires cohttp and yojson libraries *)
open Lwt
open Cohttp
open Cohttp_lwt_unix

let url = "https://aiboxapi.com/v1/audio/transcriptions"

(* Note: Multipart form data handling in OCaml requires additional libraries *)
let () =
  print_endline "使用 multipart_form 库来处理文件上传"

    import 'dart:io';
import 'package:http/http.dart' as http;

void main() async {
  final url = Uri.parse('https://aiboxapi.com/v1/audio/transcriptions');
  
  var request = http.MultipartRequest('POST', url);
  request.headers['Authorization'] = 'Bearer <token>';
  
  request.files.add(await http.MultipartFile.fromPath('file', '/path/to/audio.mp3'));
  request.fields['model'] = 'whisper-1';
  request.fields['language'] = 'zh';
  request.fields['response_format'] = 'json';
  
  var response = await request.send();
  var responseData = await response.stream.bytesToString();
  
  print(responseData);
}

    library(httr)

url <- "https://aiboxapi.com/v1/audio/transcriptions"

response <- POST(
  url,
  add_headers(Authorization = "Bearer <token>"),
  body = list(
    file = upload_file("/path/to/audio.mp3"),
    model = "whisper-1",
    language = "zh",
    response_format = "json"
  ),
  encode = "multipart"
)

cat(content(response, "text"))

    {
  "text": "这是一段测试音频的转录文本内容。"
}

    {
  "task": "transcribe",
  "language": "zh",
  "duration": 8.5,
  "text": "这是一段测试音频的转录文本内容。",
  "segments": [
    {
      "id": 0,
      "seek": 0,
      "start": 0.0,
      "end": 3.5,
      "text": "这是一段测试音频",
      "tokens": [50364, 1234, 5678],
      "temperature": 0.0,
      "avg_logprob": -0.3,
      "compression_ratio": 1.2,
      "no_speech_prob": 0.01
    }
  ]
}

    1
00:00:00,000 --> 00:00:03,500
这是一段测试音频

2
00:00:03,500 --> 00:00:08,500
的转录文本内容。

    {
  "error": {
    "code": 400,
    "message": "请求参数无效",
    "type": "invalid_request_error"
  }
}

    {
  "error": {
    "code": 401,
    "message": "身份验证失败，请检查您的API密钥",
    "type": "authentication_error"
  }
}

    {
  "error": {
    "code": 402,
    "message": "账户余额不足，请充值后再试",
    "type": "payment_required"
  }
}

    {
  "error": {
    "code": 413,
    "message": "文件大小超过限制（最大 25MB）",
    "type": "invalid_request_error"
  }
}

    {
  "error": {
    "code": 429,
    "message": "请求过于频繁，请稍后再试",
    "type": "rate_limit_error"
  }
}

    {
  "error": {
    "code": 500,
    "message": "服务器内部错误，请稍后重试",
    "type": "server_error"
  }
}

    {
  "error": {
    "code": 502,
    "message": "网关错误，服务器暂时不可用",
    "type": "bad_gateway"
  }
}

Authorizations

string 必填

所有接口均需要使用Bearer Token进行认证

获取 API Key：

访问 API Key 管理页面 获取您的 API Key

使用时在请求头中添加：

Authorization: Bearer YOUR_API_KEY

Body

⚠️ 此接口不支持在线调用（Try it）

由于文件上传的限制，请使用以下方式测试：

  • Apifox / Postman - 导入后手动将 file 参数改为文件类型
  • cURL - 参考右侧代码示例
  • SDK - 使用各语言的 SDK 示例代码
file string 必填

要转录的音频文件（文件类型）

⚠️ 注意：如果使用 Apifox 等工具测试：

  1. 导入后需要手动将此参数类型改为 file
  2. 确保请求 Content-Type 为 multipart/form-data

支持的格式：mp3, mp4, mpeg, mpga, m4a, wav, webm

最大文件大小：25 MB

model string 必填

语音识别模型名称

Example: "whisper-1"

language string

音频的语言代码（ISO-639-1 格式）

指定语言可以提高准确率和速度

支持的语言包括：zh（中文）、en（英文）、ja（日文）、ko（韩文）等 99 种语言

Example: "zh"

prompt string

可选的文本提示，用于指导模型的转录风格或延续前一段音频

最长 224 个 tokens

response_format string

输出格式

支持的格式：

  • json - JSON 格式（仅包含文本）
  • text - 纯文本
  • srt - SRT 字幕格式
  • verbose_json - 详细的 JSON 格式（包含时间戳和其他元数据）
  • vtt - WebVTT 字幕格式
temperature number

采样温度，范围 0 到 1

较高的值（如 0.8）会使输出更随机，较低的值（如 0.2）会使其更加确定和一致

Response

text string

转录后的文本内容

task string

任务类型，固定为 transcribe

仅在 verbose_json 格式时返回

language string

检测到的或指定的语言代码

仅在 verbose_json 格式时返回

duration number

音频时长（秒）

仅在 verbose_json 格式时返回

segments array

文本片段数组

仅在 verbose_json 格式时返回

属性 
  片段ID
start number 
  片段开始时间（秒）
end number 
  片段结束时间（秒）
text string 
  片段文本内容
temperature number 
  使用的采样温度
avg_logprob number 
  平均对数概率
compression_ratio number 
  压缩比
no_speech_prob number 
  无语音概率