> ## Documentation Index
> Fetch the complete documentation index at: https://gccai.heqingsong.uk/llms.txt
> Use this file to discover all available pages before exploring further.

# Whisper-1 Audio Transcription

>  - Supports speech recognition in 99 languages
- Multiple output formats: json, text, srt, vtt, etc.
- Maximum file size 25 MB 

<RequestExample>
  ```bash cURL theme={null}
  curl --request POST \
    --url https://gccai.heqingsong.uk/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=en' \
    --form 'response_format=json'
  ```

  ```python Python theme={null}
  import requests

  url = "https://gccai.heqingsong.uk/v1/audio/transcriptions"

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

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

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

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

  print(response.json())
  ```

  ```javascript JavaScript theme={null}
  const url = "https://gccai.heqingsong.uk/v1/audio/transcriptions";

  const formData = new FormData();
  formData.append("file", audioFile);
  formData.append("model", "whisper-1");
  formData.append("language", "en");
  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));
  ```

  ```go Go theme={null}
  package main

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

  func main() {
      url := "https://gccai.heqingsong.uk/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", "en")
      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))
  }
  ```

  ```java Java theme={null}
  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://gccai.heqingsong.uk/v1/audio/transcriptions";
          
          File audioFile = new File("/path/to/audio.mp3");
          
          // Use Apache HttpClient or OkHttp library for multipart/form-data requests
      }
  }
  ```

  ```php PHP theme={null}
  <?php

  $url = "https://gccai.heqingsong.uk/v1/audio/transcriptions";

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

  $data = [
      "file" => $file,
      "model" => "whisper-1",
      "language" => "en",
      "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;
  ?>
  ```

  ```ruby Ruby theme={null}
  require 'net/http'
  require 'uri'

  url = URI("https://gccai.heqingsong.uk/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', 'en'],
      ['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
  ```

  ```swift Swift theme={null}
  import Foundation

  let url = URL(string: "https://gccai.heqingsong.uk/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": "en", "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()
  ```

  ```csharp C# theme={null}
  using System;
  using System.IO;
  using System.Net.Http;
  using System.Threading.Tasks;

  class Program
  {
      static async Task Main(string[] args)
      {
          var url = "https://gccai.heqingsong.uk/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("en"), "language");
          form.Add(new StringContent("json"), "response_format");

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

          Console.WriteLine(result);
      }
  }
  ```

  ```c C theme={null}
  #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, "en",
                   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://gccai.heqingsong.uk/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;
  }
  ```

  ```objectivec Objective-C theme={null}
  #import <Foundation/Foundation.h>

  int main(int argc, const char * argv[]) {
      @autoreleasepool {
          NSURL *url = [NSURL URLWithString:@"https://gccai.heqingsong.uk/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": @"en", @"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;
  }
  ```

  ```ocaml OCaml theme={null}
  (* Requires cohttp and yojson libraries *)
  open Lwt
  open Cohttp
  open Cohttp_lwt_unix

  let url = "https://gccai.heqingsong.uk/v1/audio/transcriptions"

  (* Note: Multipart form data handling in OCaml requires additional libraries *)
  let () =
    print_endline "Use multipart_form library to handle file uploads"
  ```

  ```dart Dart theme={null}
  import 'dart:io';
  import 'package:http/http.dart' as http;

  void main() async {
    final url = Uri.parse('https://gccai.heqingsong.uk/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'] = 'en';
    request.fields['response_format'] = 'json';
    
    var response = await request.send();
    var responseData = await response.stream.bytesToString();
    
    print(responseData);
  }
  ```

  ```r R theme={null}
  library(httr)

  url <- "https://gccai.heqingsong.uk/v1/audio/transcriptions"

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

  cat(content(response, "text"))
  ```
</RequestExample>

<ResponseExample>
  ```json 200 theme={null}
  {
    "text": "This is a transcribed text from the test audio."
  }
  ```

  ```json 200 (Verbose Format) theme={null}
  {
    "task": "transcribe",
    "language": "en",
    "duration": 8.5,
    "text": "This is a transcribed text from the test audio.",
    "segments": [
      {
        "id": 0,
        "seek": 0,
        "start": 0.0,
        "end": 3.5,
        "text": "This is a transcribed text",
        "tokens": [50364, 1234, 5678],
        "temperature": 0.0,
        "avg_logprob": -0.3,
        "compression_ratio": 1.2,
        "no_speech_prob": 0.01
      }
    ]
  }
  ```

  ```srt 200 (SRT Subtitle Format) theme={null}
  1
  00:00:00,000 --> 00:00:03,500
  This is a transcribed text

  2
  00:00:03,500 --> 00:00:08,500
  from the test audio.
  ```

  ```json 400 theme={null}
  {
    "error": {
      "code": 400,
      "message": "Invalid request parameters",
      "type": "invalid_request_error"
    }
  }
  ```

  ```json 401 theme={null}
  {
    "error": {
      "code": 401,
      "message": "Authentication failed, please check your API key",
      "type": "authentication_error"
    }
  }
  ```

  ```json 402 theme={null}
  {
    "error": {
      "code": 402,
      "message": "Insufficient account balance, please recharge",
      "type": "payment_required"
    }
  }
  ```

  ```json 413 theme={null}
  {
    "error": {
      "code": 413,
      "message": "File size exceeds limit (maximum 25MB)",
      "type": "invalid_request_error"
    }
  }
  ```

  ```json 429 theme={null}
  {
    "error": {
      "code": 429,
      "message": "Too many requests, please try again later",
      "type": "rate_limit_error"
    }
  }
  ```

  ```json 500 theme={null}
  {
    "error": {
      "code": 500,
      "message": "Internal server error, please try again later",
      "type": "server_error"
    }
  }
  ```

  ```json 502 theme={null}
  {
    "error": {
      "code": 502,
      "message": "Bad gateway, server temporarily unavailable",
      "type": "bad_gateway"
    }
  }
  ```
</ResponseExample>

## Authorizations

<ParamField header="Authorization" type="string" required>
  All interfaces require Bearer Token authentication

  Get API Key:

  Visit [API Key Management Page](https://gccai.heqingsong.uk/keys) to get your API Key

  Add to request header:

  ```
  Authorization: Bearer YOUR_API_KEY
  ```
</ParamField>

## Body

<Note>
  **⚠️ Online testing (Try it) is not supported for this endpoint**

  Due to file upload limitations, please test using:

  * **Apifox / Postman** - Manually change `file` parameter to file type after importing
  * **cURL** - Refer to code examples on the right
  * **SDK** - Use SDK examples in various languages
</Note>

<ParamField body="file" type="string" format="binary" required>
  Audio file to transcribe (File type)

  **⚠️ Note**: When testing with Apifox or similar tools:

  1. After importing, manually change this parameter type to `file`
  2. Ensure request Content-Type is `multipart/form-data`

  Supported formats: mp3, mp4, mpeg, mpga, m4a, wav, webm

  Maximum file size: 25 MB
</ParamField>

<ParamField body="model" type="string" default="whisper-1" required>
  Speech recognition model name

  Example: `"whisper-1"`
</ParamField>

<ParamField body="language" type="string">
  Language code of the audio (ISO-639-1 format)

  Specifying the language can improve accuracy and speed

  Supported languages include: zh (Chinese), en (English), ja (Japanese), ko (Korean), and 99 other languages

  Example: `"en"`
</ParamField>

<ParamField body="prompt" type="string">
  Optional text prompt to guide the transcription style or continue from previous audio

  Maximum 224 tokens
</ParamField>

<ParamField body="response_format" type="string" default="json">
  Output format

  Supported formats:

  * `json` - JSON format (text only)
  * `text` - Plain text
  * `srt` - SRT subtitle format
  * `verbose_json` - Verbose JSON format (includes timestamps and metadata)
  * `vtt` - WebVTT subtitle format
</ParamField>

<ParamField body="temperature" type="number" default="0">
  Sampling temperature, range 0 to 1

  Higher values (like 0.8) make output more random, lower values (like 0.2) make it more deterministic and consistent
</ParamField>

## Response

<ResponseField name="text" type="string">
  Transcribed text content
</ResponseField>

<ResponseField name="task" type="string">
  Task type, fixed as `transcribe`

  Only returned in verbose\_json format
</ResponseField>

<ResponseField name="language" type="string">
  Detected or specified language code

  Only returned in verbose\_json format
</ResponseField>

<ResponseField name="duration" type="number">
  Audio duration (seconds)

  Only returned in verbose\_json format
</ResponseField>

<ResponseField name="segments" type="array">
  Array of text segments

  Only returned in verbose\_json format

  <Expandable title="Properties">
    <ResponseField name="id" type="integer">
      Segment ID
    </ResponseField>

    <ResponseField name="start" type="number">
      Segment start time (seconds)
    </ResponseField>

    <ResponseField name="end" type="number">
      Segment end time (seconds)
    </ResponseField>

    <ResponseField name="text" type="string">
      Segment text content
    </ResponseField>

    <ResponseField name="temperature" type="number">
      Sampling temperature used
    </ResponseField>

    <ResponseField name="avg_logprob" type="number">
      Average log probability
    </ResponseField>

    <ResponseField name="compression_ratio" type="number">
      Compression ratio
    </ResponseField>

    <ResponseField name="no_speech_prob" type="number">
      No speech probability
    </ResponseField>
  </Expandable>
</ResponseField>