Python을 사용하여 Tencent Cloud 인터페이스와 연결하여 실시간 음성 전사 기능 실현

pip install requests

import requests
import json

def recognize_speech(audio_file, secret_id, secret_key):
    # 设置请求地址及参数
    url = 'https://s.tencentcloudapi.com/'
    params = {
        'Action': 'CreateASRTask',
        'Version': '2019-12-12',
        'Region': 'ap-guangzhou',
        'Timestamp': int(time.time()),
        'Nonce': random.randint(1, 10000),
        'SecretId': secret_id,
        'SignatureMethod': 'HmacSHA256',
    }

    # 计算签名
    sorted_params = sorted(params.items(), key=lambda x: x[0])
    query_string = urlencode(sorted_params, quote_via=quote_plus)
    src_str = 'POSTs.tencentcloudapi.com/?' + query_string
    signature = base64.b64encode(hmac.new(secret_key.encode('utf-8'), src_str.encode('utf-8'), hashlib.sha256).digest()).decode('utf-8')
    params['Signature'] = signature

    # 读取音频文件
    with open(audio_file, 'rb') as f:
        file_content = base64.b64encode(f.read()).decode('utf-8')

    # 构造请求数据
    data = {
        'TaskConfig': {
            'EngineModelType': '16k_zh',
        },
        'Data': {
            'Url': '',
            'Data': file_content,
        },
    }

    # 发送请求
    response = requests.post(url, data=json.dumps(data), params=params)

    # 解析返回结果
    result = json.loads(response.text)
    return result

if __name__ == '__main__':
    audio_file = 'test.wav'
    secret_id = 'your_secret_id'
    secret_key = 'your_secret_key'
    result = recognize_speech(audio_file, secret_id, secret_key)
    print(result)