add ali voice output

增加阿里云语音输出支持。

voice/ali/ali_api.py

@@ -0,0 +1,114 @@
+# coding=utf-8
+"""
+Author: chazzjimel
+Email: chazzjimel@gmail.com
+wechat：cheung-z-x
+
+Description:
+
+"""
+import json
+import time
+
+import requests
+import datetime
+import hashlib
+import hmac
+import base64
+import urllib.parse
+import uuid
+
+from common.log import logger
+from common.tmp_dir import TmpDir
+
+
+def text_to_speech_aliyun(url, text, appkey, token):
+    # 请求的headers
+    headers = {
+        "Content-Type": "application/json",
+    }
+
+    # 请求的payload
+    data = {
+        "text": text,
+        "appkey": appkey,
+        "token": token,
+        "format": "wav"
+    }
+
+    # 发送POST请求
+    response = requests.post(url, headers=headers, data=json.dumps(data))
+
+    # 检查响应状态码和内容类型
+    if response.status_code == 200 and response.headers['Content-Type'] == 'audio/mpeg':
+        # 构造唯一的文件名
+        output_file = TmpDir().path() + "reply-" + str(int(time.time())) + "-" + str(hash(text) & 0x7FFFFFFF) + ".wav"
+
+        # 将响应内容写入文件
+        with open(output_file, 'wb') as file:
+            file.write(response.content)
+        logger.debug(f"音频文件保存成功，文件名：{output_file}")
+    else:
+        # 打印错误信息
+        logger.debug("响应状态码: {}".format(response.status_code))
+        logger.debug("响应内容: {}".format(response.text))
+        output_file = None
+
+    return output_file
+
+
+class AliyunTokenGenerator:
+    def __init__(self, access_key_id, access_key_secret):
+        self.access_key_id = access_key_id
+        self.access_key_secret = access_key_secret
+
+    def sign_request(self, parameters):
+        # 将参数排序
+        sorted_params = sorted(parameters.items())
+
+        # 构造待签名的字符串
+        canonicalized_query_string = ''
+        for (k, v) in sorted_params:
+            canonicalized_query_string += '&' + self.percent_encode(k) + '=' + self.percent_encode(v)
+
+        string_to_sign = 'GET&%2F&' + self.percent_encode(canonicalized_query_string[1:])  # 使用GET方法
+
+        # 计算签名
+        h = hmac.new((self.access_key_secret + "&").encode('utf-8'), string_to_sign.encode('utf-8'), hashlib.sha1)
+        signature = base64.encodebytes(h.digest()).strip()
+
+        return signature
+
+    def percent_encode(self, encode_str):
+        encode_str = str(encode_str)
+        res = urllib.parse.quote(encode_str, '')
+        res = res.replace('+', '%20')
+        res = res.replace('*', '%2A')
+        res = res.replace('%7E', '~')
+        return res
+
+    def get_token(self):
+        # 设置请求参数
+        params = {
+            'Format': 'JSON',
+            'Version': '2019-02-28',
+            'AccessKeyId': self.access_key_id,
+            'SignatureMethod': 'HMAC-SHA1',
+            'Timestamp': datetime.datetime.utcnow().strftime("%Y-%m-%dT%H:%M:%SZ"),
+            'SignatureVersion': '1.0',
+            'SignatureNonce': str(uuid.uuid4()),  # 使用uuid生成唯一的随机数
+            'Action': 'CreateToken',
+            'RegionId': 'cn-shanghai'
+        }
+
+        # 计算签名
+        signature = self.sign_request(params)
+        params['Signature'] = signature
+
+        # 构造请求URL
+        url = 'http://nls-meta.cn-shanghai.aliyuncs.com/?' + urllib.parse.urlencode(params)
+
+        # 发送请求
+        response = requests.get(url)
+
+        return response.text

voice/ali/ali_voice.py

@@ -0,0 +1,74 @@
+# -*- coding: utf-8 -*-
+"""
+Author: chazzjimel
+Email: chazzjimel@gmail.com
+wechat：cheung-z-x
+
+Description:
+ali voice service
+
+"""
+import json
+import os
+import re
+import time
+
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from voice.voice import Voice
+from voice.ali.ali_api import AliyunTokenGenerator
+from voice.ali.ali_api import text_to_speech_aliyun
+
+
+def textContainsEmoji(text):
+    # 此正则表达式匹配大多数表情符号和特殊字符
+    pattern = re.compile(
+        '[\U0001F600-\U0001F64F\U0001F300-\U0001F5FF\U0001F680-\U0001F6FF\U0001F700-\U0001F77F\U0001F780-\U0001F7FF\U0001F800-\U0001F8FF\U0001F900-\U0001F9FF\U0001FA00-\U0001FA6F\U0001FA70-\U0001FAFF\U00002702-\U000027B0\U00002600-\U000026FF]')
+    return bool(pattern.search(text))
+
+
+class AliVoice(Voice):
+    def __init__(self):
+        try:
+            curdir = os.path.dirname(__file__)
+            config_path = os.path.join(curdir, "config.json")
+            with open(config_path, "r") as fr:
+                config = json.load(fr)
+            self.token = None
+            self.token_expire_time = 0
+            self.api_url = config.get("api_url")
+            self.appkey = config.get("appkey")
+            self.access_key_id = config.get("access_key_id")
+            self.access_key_secret = config.get("access_key_secret")
+        except Exception as e:
+            logger.warn("AliVoice init failed: %s, ignore " % e)
+
+    # def voiceToText(self, voice_file):
+    #     pass
+
+    def textToVoice(self, text):
+        text = re.sub(r'[^\u4e00-\u9fa5\u3040-\u30FF\uAC00-\uD7AFa-zA-Z0-9'
+                      r'äöüÄÖÜáéíóúÁÉÍÓÚàèìòùÀÈÌÒÙâêîôûÂÊÎÔÛçÇñÑ，。！？,.]', '', text)
+        # 提取 token_id 值
+        token_id = self.get_valid_token()
+        fileName = text_to_speech_aliyun(self.api_url, text, self.appkey, token_id)
+        if fileName:
+            logger.info("[Ali] textToVoice text={} voice file name={}".format(text, fileName))
+            reply = Reply(ReplyType.VOICE, fileName)
+        else:
+            reply = Reply(ReplyType.ERROR, "抱歉，语音合成失败")
+        return reply
+
+    def get_valid_token(self):
+        current_time = time.time()
+        if self.token is None or current_time >= self.token_expire_time:
+            get_token = AliyunTokenGenerator(self.access_key_id, self.access_key_secret)
+            token_str = get_token.get_token()
+            token_data = json.loads(token_str)
+            self.token = token_data["Token"]["Id"]
+            # 将过期时间减少一小段时间（例如5分钟），以避免在边界条件下的过期
+            self.token_expire_time = token_data["Token"]["ExpireTime"] - 300
+            logger.debug(f"新获取的阿里云token：{self.token}")
+        else:
+            logger.debug("使用缓存的token")
+        return self.token

voice/ali/config.json.template

@@ -0,0 +1,6 @@
+{
+    "api_url": "https://nls-gateway-cn-shanghai.aliyuncs.com/stream/v1/tts",
+    "appkey": "",
+    "access_key_id": "",
+    "access_key_secret": ""
+}

voice/factory.py

@@ -29,12 +29,8 @@ def create_voice(voice_type):
         from voice.azure.azure_voice import AzureVoice
 
         return AzureVoice()
-    elif voice_type == "elevenlabs":
+    elif voice_type == "ali":
-        from voice.elevent.elevent_voice import ElevenLabsVoice
+        from voice.ali.ali_voice import AliVoice
 
-        return ElevenLabsVoice()
+        return AliVoice()
-
-    elif voice_type == "linkai":
-        from voice.linkai.linkai_voice import LinkAIVoice
-        return LinkAIVoice()
     raise RuntimeError