Browse Source

add ali voice output

增加阿里云语音输出支持。
master
chazzjimel 11 months ago
parent
commit
d89b056886
4 changed files with 197 additions and 7 deletions
  1. +114
    -0
      voice/ali/ali_api.py
  2. +74
    -0
      voice/ali/ali_voice.py
  3. +6
    -0
      voice/ali/config.json.template
  4. +3
    -7
      voice/factory.py

+ 114
- 0
voice/ali/ali_api.py View File

@@ -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

+ 74
- 0
voice/ali/ali_voice.py View File

@@ -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

+ 6
- 0
voice/ali/config.json.template View File

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

+ 3
- 7
voice/factory.py View File

@@ -29,12 +29,8 @@ def create_voice(voice_type):
from voice.azure.azure_voice import AzureVoice

return AzureVoice()
elif voice_type == "elevenlabs":
from voice.elevent.elevent_voice import ElevenLabsVoice
elif voice_type == "ali":
from voice.ali.ali_voice import AliVoice

return ElevenLabsVoice()

elif voice_type == "linkai":
from voice.linkai.linkai_voice import LinkAIVoice
return LinkAIVoice()
return AliVoice()
raise RuntimeError

Loading…
Cancel
Save