GPT-4o 转录

POST https://api.quickrouter.ai/v1/audio/transcriptions 在线调试 →

▼ Authorization

在 Header 添加参数 Authorization，其值为 Bearer 之后拼接 Token

示例： Authorization: Bearer ********************

请求参数

Header 参数

Content-Type string

必需

示例: application/json

Authorization string

必需

示例: Bearer $OPENAI_API_KEY

Body 参数 multipart/form-data

file file

必需

要转录的音频文件对象，格式为：flac、mp3、mp4、mpeg、mpga、m4a、ogg、wav 或 webm。

model string

必需

要使用的模型 ID，如 gpt-4o-transcribe。

response_format string

可选

转录输出格式：json、text、srt、verbose_json 或 vtt。

请求示例代码

curl --location --request POST 'https://api.quickrouter.ai/v1/audio/transcriptions' \
--header 'Authorization: Bearer <token>' \
--form 'file=@"/path/to/test.m4a"' \
--form 'model="gpt-4o-transcribe"' \
--form 'response_format="json"'

var myHeaders = new Headers();
myHeaders.append("Authorization", "Bearer <token>");

var formdata = new FormData();
formdata.append("file", fileInput.files[0], "test.m4a");
formdata.append("model", "gpt-4o-transcribe");
formdata.append("response_format", "json");

var requestOptions = {
   method: 'POST',
   headers: myHeaders,
   body: formdata,
   redirect: 'follow'
};

fetch("https://api.quickrouter.ai/v1/audio/transcriptions", requestOptions)
   .then(response => response.text())
   .then(result => console.log(result))
   .catch(error => console.log('error', error));

import http.client
import mimetypes
from codecs import encode

conn = http.client.HTTPSConnection("api.quickrouter.ai")
dataList = []
boundary = 'wL36Yn8afVp8Ag7AmP8qZ0SA4n1v9T'
dataList.append(encode('--' + boundary))
dataList.append(encode('Content-Disposition: form-data; name=file; filename={0}'.format('/path/to/test.m4a')))

fileType = mimetypes.guess_type('/path/to/test.m4a')[0] or 'application/octet-stream'
dataList.append(encode('Content-Type: {}'.format(fileType)))
dataList.append(encode(''))

with open('/path/to/test.m4a', 'rb') as f:
   dataList.append(f.read())
dataList.append(encode('--' + boundary))
dataList.append(encode('Content-Disposition: form-data; name=model;'))
dataList.append(encode(''))
dataList.append(encode('gpt-4o-transcribe'))
dataList.append(encode('--'+boundary+'--'))
body = b'\r\n'.join(dataList)
payload = body
headers = {
   'Authorization': 'Bearer <token>',
   'Content-type': 'multipart/form-data; boundary={}'.format(boundary)
}
conn.request("POST", "/v1/audio/transcriptions", payload, headers)
res = conn.getresponse()
data = res.read()
print(data.decode("utf-8"))

返回响应

响应参数 🟢 200 OK · application/json

text string

必需

转录出的文本内容。

示例

{
  "text": "Imagine the wildest idea that you've ever had, and you're curious about how it might scale to something that's a 100, a 1,000 times bigger. This is a place where you can get to do that."
}