中文语音转文本 (ASR) PRO

2 IC每60秒

✓ 活跃 语音 LLM

试用演示

试用 AI 演示

登录或创建免费账户来使用此 AI 服务演示并探索我们强大的 API。

注册即可获得 100 积分 (IC) 免费赠送！

优惠截止至 2025 年 12 月 31 日

免费创建账户登录

Example File (Click to try)

Selected: john-china.wav

API Key

Log in to use your API keys or Create an account

Endpoint URL

cURL Command

选择您的分块大小

Upload Audio File

入门

先决条件

• 来自 iApp Technology 的 API 密钥
• 支持格式的音频文件
• 最长文件长度：不超过 1 小时

主要特点

• 从音频文件中提取文本
• 说话人分离，支持多说话人对话
• 支持多种音频格式
• 上下文感知的高精度转录

安全与合规

• API 密钥认证
• 符合 GDPR 和 PDPA

API 端点

端点	方法	描述	费用
/v3/store/speech/speech-to-text/pro/zh 旧版: /asr/v3/zh/pro	POST	将中文语音转换为文本（使用 LLM 的 Pro 模型）	2 IC / 60 秒

API 用法

支持的文件格式

API 支持以下音频和视频文件格式：

• 音频：.mp3, .wav, .m4a, .aac, .aif, .cda, .flac, .mid, .ogg, .wma

端点: POST /v3/store/speech/speech-to-text/pro/zh

标头:

• Content-Type: multipart/form-data
• apikey: 您的 API 密钥用于身份验证

表单参数:

参数	类型	必需	默认值	描述
file	文件	是	-	要转录的音频文件
prompt	字符串	否	"base"	要使用的提示模板
chunk_size	整数	否	20	处理音频块的秒数大小
use_asr_pro	布尔值	否	true	使用 ASR Pro 模型

示例请求:

curl -X POST "https://api.iapp.co.th/v3/store/speech/speech-to-text/pro/zh" \
  -H "Content-Type: multipart/form-data" \
  -H "apikey: YOUR_API_KEY" \
  -F "file=@/path/to/your/audio.mp3" \
  -F "prompt=base" \
  -F "chunk_size=20" \
  -F "use_asr_pro=true"

示例响应:

{
    "output": [
        {
            "text": "第一段转录文本。",
            "start": 0.0,
            "end": 5.28,
            "speaker": "SPEAKER_00",
            "segment": 0
        },
        {
            "text": "第二段转录文本。",
            "start": 5.28,
            "end": 10.56,
            "speaker": "SPEAKER_01",
            "segment": 1
        }
    ],
    "audio_duration_in_seconds": 60.5,
    "uploaded_file_name": "example.mp3",
    "processing_time_in_seconds": 12.34,
    "use_asr_pro": true,
    "asr_pro_is_used": true,
    "iapp": {
        "seconds": 60.5
    }
}

响应状态码

• 200 OK: 请求成功
• 400 Bad Request: 无效请求（例如，未上传文件，不支持的文件格式）
• 404 Not Found: 任务 ID 未找到
• 500 Internal Server Error: 处理失败，服务器错误

注意事项

• 支持说话人分离，每个分段都包含说话人 ID 和时间戳信息。

代码示例

Curl

curl -X POST https://api.iapp.co.th/v3/store/speech/speech-to-text/pro/zh \
    -H "apikey: YOUR_API_KEY" \
    -F "file=@/path/to/audio.mp3"

Python 示例

import requests

def transcribe_audio(file_path, api_key):
    url = "https://api.iapp.co.th/v3/store/speech/speech-to-text/pro/zh"
    headers = {"apikey": api_key}

    files = {"file": open(file_path, "rb")}
    data = {
        "prompt": "base",
        "chunk_size": 20,
        "use_asr_pro": true
    }

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

    if response.status_code == 200:
        return response.json()
    else:
        return f"Error: {response.status_code}, {response.text}"

JavaScript 示例

async function transcribeAudio(filePath, apiKey) {
    const url = "https://api.iapp.co.th/v3/store/speech/speech-to-text/pro/zh"

    const formData = new FormData()
    formData.append("file", await fetch(filePath).then((r) => r.blob()))
    formData.append("prompt", "base")
    formData.append("chunk_size", "20")
    formData.append("use_asr_pro", "true")

    const response = await fetch(url, {
        method: "POST",
        headers: {
            apikey: apiKey,
        },
        body: formData,
    })

    if (response.ok) {
        return await response.json()
    } else {
        throw new Error(`Error: ${response.status}, ${await response.text()}`)
    }
}

PHP 示例

function transcribe_audio($file_path, $api_key) {
    $url = "https://api.iapp.co.th/v3/store/speech/speech-to-text/pro/zh";

    $curl = curl_init();

    $post_data = [
        'file' => new CURLFile($file_path),
        'prompt' => 'base',
        'chunk_size' => '20',
        'use_asr_pro' => 'true'
    ];

    curl_setopt_array($curl, [
        CURLOPT_URL => $url,
        CURLOPT_RETURNTRANSFER => true,
        CURLOPT_POST => true,
        CURLOPT_POSTFIELDS => $post_data,
        CURLOPT_HTTPHEADER => [
            "apikey: $api_key"
        ]
    ]);

    $response = curl_exec($curl);
    $status_code = curl_getinfo($curl, CURLINFO_HTTP_CODE);
    curl_close($curl);

    if ($status_code === 200) {
        return json_decode($response, true);
    } else {
        return "Error: $status_code, $response";
    }
}

// Usage
$result = transcribe_audio("path/to/audio.mp3", "YOUR_API_KEY");
print_r($result);

Swift 示例

import Foundation

func transcribeAudio(filePath: String, apiKey: String, completion: @escaping (Result<[String: Any], Error>) -> Void) {
    let url = URL(string: "https://api.iapp.co.th/v3/store/speech/speech-to-text/pro/zh")!

    var request = URLRequest(url: url)
    request.httpMethod = "POST"
    request.addValue(apiKey, forHTTPHeaderField: "apikey")

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

    let fileURL = URL(fileURLWithPath: filePath)
    guard let fileData = try? Data(contentsOf: fileURL) else {
        completion(.failure(NSError(domain: "", code: 0, userInfo: [NSLocalizedDescriptionKey: "无法加载文件"])))
        return
    }

    var body = Data()
    let filename = fileURL.lastPathComponent

    // 添加文件
    body.append("--\(boundary)\r\n".data(using: .utf8)!)
    body.append("Content-Disposition: form-data; name=\"file\"; filename=\"\(filename)\"\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)!)

    // 添加 prompt
    body.append("--\(boundary)\r\n".data(using: .utf8)!)
    body.append("Content-Disposition: form-data; name=\"prompt\"\r\n\r\n".data(using: .utf8)!)
    body.append("base".data(using: .utf8)!)
    body.append("\r\n".data(using: .utf8)!)

    // 添加 chunk_size
    body.append("--\(boundary)\r\n".data(using: .utf8)!)
    body.append("Content-Disposition: form-data; name=\"chunk_size\"\r\n\r\n".data(using: .utf8)!)
    body.append("20".data(using: .utf8)!)
    body.append("\r\n".data(using: .utf8)!)

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

    request.httpBody = body

    URLSession.shared.dataTask(with: request) { data, response, error in
        if let error = error {
            completion(.failure(error))
            return
        }

        guard let data = data else {
            completion(.failure(NSError(domain: "", code: 0, userInfo: [NSLocalizedDescriptionKey: "未收到数据"])))
            return
        }

        do {
            if let json = try JSONSerialization.jsonObject(with: data) as? [String: Any] {
                completion(.success(json))
            } else {
                completion(.failure(NSError(domain: "", code: 0, userInfo: [NSLocalizedDescriptionKey: "无效的 JSON 格式"])))
            }
        } catch {
            completion(.failure(error))
        }
    }.resume()
}

// Usage
transcribeAudio(filePath: "path/to/audio.mp3", apiKey: "YOUR_API_KEY") { result in
    switch result {
    case .success(let json):
        print(json)
    case .failure(let error):
        print("Error: \(error)")
    }
}

Kotlin 示例

import okhttp3.*
import java.io.File
import java.io.IOException

fun transcribeAudio(filePath: String, apiKey: String, callback: (Result<String>) -> Unit) {
    val client = OkHttpClient()
    val file = File(filePath)

    val requestBody = MultipartBody.Builder()
        .setType(MultipartBody.FORM)
        .addFormDataPart(
            "file",
            file.name,
            RequestBody.create(MediaType.parse("audio/*"), file)
        )
        .addFormDataPart("prompt", "base")
        .addFormDataPart("chunk_size", "20")
        .addFormDataPart("use_asr_pro", "true")
        .build()

    val request = Request.Builder()
        .url("https://api.iapp.co.th/v3/store/speech/speech-to-text/pro/zh")
        .header("apikey", apiKey)
        .post(requestBody)
        .build()

    client.newCall(request).enqueue(object : Callback {
        override fun onFailure(call: Call, e: IOException) {
            callback(Result.failure(e))
        }

        override fun onResponse(call: Call, response: Response) {
            if (response.isSuccessful) {
                callback(Result.success(response.body()?.string() ?: ""))
            } else {
                callback(Result.failure(IOException("Error: ${response.code()} ${response.message()}")))
            }
        }
    })
}

Java 示例

import java.io.File;
import java.io.IOException;
import okhttp3.*;

public class ASRApiClient {

    public static void transcribeAudio(String filePath, String apiKey, Callback callback) {
        OkHttpClient client = new OkHttpClient();
        File file = new File(filePath);

        RequestBody requestBody = new MultipartBody.Builder()
                .setType(MultipartBody.FORM)
                .addFormDataPart(
                        "file",
                        file.getName(),
                        RequestBody.create(MediaType.parse("audio/*"), file)
                )
                .addFormDataPart("prompt", "base")
                .addFormDataPart("chunk_size", "20")
                .addFormDataPart("use_asr_pro", "true")
                .build();

        Request request = new Request.Builder()
                .url("https://api.iapp.co.th/v3/store/speech/speech-to-text/pro/zh")
                .header("apikey", apiKey)
                .post(requestBody)
                .build();

        client.newCall(request).enqueue(callback);
    }

    public static void main(String[] args) {
        transcribeAudio("path/to/audio.mp3", "YOUR_API_KEY", new Callback() {
            @Override
            public void onFailure(Call call, IOException e) {
                System.err.println("Error: " + e.getMessage());
            }

            @Override
            public void onResponse(Call call, Response response) throws IOException {
                if (response.isSuccessful()) {
                    System.out.println(response.body().string());
                } else {
                    System.err.println("Error: " + response.code() + " " + response.message());
                }
            }
        });
    }
}

Dart (Flutter) 示例

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

Future<Map<String, dynamic>> transcribeAudio(String filePath, String apiKey) async {
  var uri = Uri.parse('https://api.iapp.co.th/v3/store/speech/speech-to-text/pro/zh');

  var request = http.MultipartRequest('POST', uri);
  request.headers['apikey'] = apiKey;

  request.files.add(await http.MultipartFile.fromPath(
    'file',
    filePath,
  ));

  request.fields['prompt'] = 'base';
  request.fields['chunk_size'] = '20';
  request.fields['use_asr_pro'] = 'true';

  try {
    var response = await request.send();
    var responseData = await http.Response.fromStream(response);

    if (response.statusCode == 200) {
      return jsonDecode(responseData.body);
    } else {
      throw Exception('Failed to transcribe: ${response.statusCode} ${responseData.body}');
    }
  } catch (e) {
    throw Exception('Error transcribing file: $e');
  }
}

定价

操作	生产路径	旧版路径	IC 费用	单位	本地部署
中文语音转文本 (Pro)	/v3/store/speech/speech-to-text/pro/zh	/asr/v3/zh/pro	2 IC	每 60 秒	联系我们