腾讯云语音合成TTS试用

import os
from dotenv import load_dotenv
root_dir='/mnt/workspace/'
load_dotenv(os.path.join(root_dir, "TTS.env"))
APPID =os.getenv('APPID')
SECRET_ID =os.getenv('SECRET_ID')
SECRET_KEY =os.getenv('SECRET_KEY')

import hmac
import hashlib
import json
import time
from datetime import datetime
from uuid import uuid4
import base64
from http.client import HTTPSConnection
from IPython.display import Audio
import io

def sign(key, msg):
    return hmac.new(key, msg.encode("utf-8"), hashlib.sha256).digest()

TEXT =  """请相信，每一个努力的瞬间，都是你人生故事中不可或缺的篇章。
 """
VOICETYPE = 301006 # 音色类型
CODEC = "wav" # 音频格式：pcm/mp3
SAMPLE_RATE = 16000 # 音频采样率：8000/16000
ENABLE_SUBTITLE = True

def text_to_speech(text, voice_type=VOICETYPE, sample_rate=SAMPLE_RATE, codec=CODEC, enable_subtitle=ENABLE_SUBTITLE,EmotionCategory='sad'):
        service = "tts"
        host = "tts.tencentcloudapi.com"
        region = "ap-shanghai"
        version = "2019-08-23"
        action = "TextToVoice"
        token = ""
        # 使用提供的参数更新 payload 字典
        payload = {
            "Text": text,
            "VoiceType": voice_type,
            "SampleRate": sample_rate,
            "Codec": codec,
            "EnableSubtitle": enable_subtitle,
            "EmotionCategory": EmotionCategory,
            "SessionId": str(uuid4())  # 生成唯一会话 ID
        }
        params = json.dumps(payload)
        endpoint = "https://tts.tencentcloudapi.com"
        algorithm = "TC3-HMAC-SHA256"
        timestamp = int(time.time())
        date = datetime.utcfromtimestamp(timestamp).strftime("%Y-%m-%d")
        # ************* 步骤 1：拼接规范请求串 *************
        http_request_method = "POST"
        canonical_uri = "/"
        canonical_querystring = ""
        ct = "application/json; charset=utf-8"
        canonical_headers = "content-type:%s\nhost:%s\nx-tc-action:%s\n" % (ct, host, action.lower())
        signed_headers = "content-type;host;x-tc-action"
        hashed_request_payload = hashlib.sha256(params.encode("utf-8")).hexdigest()
        canonical_request = (http_request_method + "\n" +
                             canonical_uri + "\n" +
                             canonical_querystring + "\n" +
                             canonical_headers + "\n" +
                             signed_headers + "\n" +
                             hashed_request_payload)
        # ************* 步骤 2：拼接待签名字符串 *************
        credential_scope = date + "/" + service + "/" + "tc3_request"
        hashed_canonical_request = hashlib.sha256(canonical_request.encode("utf-8")).hexdigest()
        string_to_sign = (algorithm + "\n" +
                          str(timestamp) + "\n" +
                          credential_scope + "\n" +
                          hashed_canonical_request)
        # ************* 步骤 3：计算签名 *************
        secret_date = sign(("TC3" + SECRET_KEY).encode("utf-8"), date)
        secret_service = sign(secret_date, service)
        secret_signing = sign(secret_service, "tc3_request")
        signature = hmac.new(secret_signing, string_to_sign.encode("utf-8"), hashlib.sha256).hexdigest()
        # ************* 步骤 4：拼接 Authorization *************
        authorization = (algorithm + " " +
                         "Credential=" + SECRET_ID + "/" + credential_scope + ", " +
                         "SignedHeaders=" + signed_headers + ", " +
                         "Signature=" + signature)
        # ************* 步骤 5：构造并发起请求 *************
        headers = {
            "Authorization": authorization,
            "Content-Type": "application/json; charset=utf-8",
            "Host": host,
            "X-TC-Action": action,
            "X-TC-Timestamp": timestamp,
            "X-TC-Version": version
        }
        if region:
            headers["X-TC-Region"] = region
        if token:
            headers["X-TC-Token"] = token
        print('start-----')
        try:
            req = HTTPSConnection(host)
            req.request("POST", "/", headers=headers, body=params.encode("utf-8"))
            resp = req.getresponse()
            # 假设我们成功获取了音频数据并保存到了 audio_file_path
            # 解码 JSON 响应体
            response_json = json.loads(resp.read().decode('utf-8'))
            # # 获取 Base64 编码的音频数据
            base64_audio = response_json['Response']
            return base64_audio
        except Exception as err:
            print(err)

rest=text_to_speech(TEXT,VOICETYPE, SAMPLE_RATE,CODEC,ENABLE_SUBTITLE)
Audio(base64.b64decode(rest['Audio'].encode("utf-8")), autoplay=True)