讯飞云 API 语音听写 python3 调用例程

#!/usr/bin/python3
# -*- coding: UTF-8 -*-

import requests
import time
import gzip
import urllib
import json
import hashlib
import base64

def audio_dictation():
    """
    讯飞语音听写 API 调用例程
    注意：使用前需要在讯飞云控制台中的IP白名单中加入本机IP！
    参考：讯飞云官方 API 文档 https://doc.xfyun.cn/rest_api/语音听写.html
    """

    # 读取 APPID：
    with open('./appid', mode='r', encoding='ASCII') as appid_file:
        x_appid = appid_file.read()

    # 读取APIKey：
    with open('./apikey', mode='r', encoding='ASCII') as apikey_file:
        api_key = apikey_file.read()

    # API URL：
    url = 'http://api.xfyun.cn/v1/service/v1/iat'

    # 读取音频文件内容 (将 `zhngjb_clip.wav` 替换成需要上传的音频文件)：
    with open('./zhngjb_clip.wav', mode='rb') as audio_file:
        file_content = audio_file.read()

    # 对音频文件进行 base64 音频编码：
    base64_audio = base64.b64encode(file_content)
    body = urllib.parse.urlencode({'audio': base64_audio})

    # 采样率 16k，编码格式 未压缩：
    param = {"engine_type": "sms16k", "aue": "raw"} 

    # 构建 header：
    x_param = base64.b64encode(json.dumps(param).replace(' ', '').encode())
    x_time = str(int(int(round(time.time() * 1000)) / 1000))
    x_checksum = hashlib.md5(api_key.encode() + str(x_time).encode() + x_param).hexdigest()
    x_header = {'X-Appid': x_appid,
                'X-CurTime': x_time,
                'X-Param': x_param,
                'X-CheckSum': x_checksum}

    req_header = {'Content-Type': 'application/x-www-form-urlencoded',
                  'charset': 'utf-8'}

    headers = {**req_header, **x_header}   

    # 发送请求：
    start = time.time()
    response = requests.post(url, headers=headers, data=body)
    duration = time.time() - start

    with open('result', mode='w', encoding='utf-8') as result_file:
        print(f'Request sent. Duration: {duration}s\n'
              f'status code = {response.status_code}\n'
              f'headers = {response.headers}\n'
              f'content = {response.content.decode("utf-8")}', file=result_file)

if __name__ == '__main__':
    audio_dictation()