update qrcode

README.md

@@ -90,6 +90,13 @@ pip3 install -r requirements.txt
 
 参考[#415](https://github.com/zhayujie/chatgpt-on-wechat/issues/415)
 
+使用`azure`语音功能需安装依赖:
+```bash
+pip3 install azure-cognitiveservices-speech
+```
+> 目前默认发布的镜像和`railway`部署，都基于`apline`，无法安装`azure`的依赖。若有需求请自行基于[`debian`](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/docker/Dockerfile.debian.latest)打包。
+参考[文档](https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/quickstarts/setup-platform?pivots=programming-language-python&tabs=linux%2Cubuntu%2Cdotnet%2Cjre%2Cmaven%2Cnodejs%2Cmac%2Cpypi)
+
 ## 配置
 
 配置文件的模板在根目录的`config-template.json`中，需复制该模板创建最终生效的 `config.json` 文件：

app.py

@@ -1,5 +1,6 @@
 # encoding:utf-8
 
+import os
 from config import conf, load_config
 from channel import channel_factory
 from common.log import logger
@@ -13,6 +14,10 @@ def run():
 
         # create channel
         channel_name=conf().get('channel_type', 'wx')
+        if channel_name == 'wxy':
+            os.environ['WECHATY_LOG']="warn"
+            # os.environ['WECHATY_PUPPET_SERVICE_ENDPOINT'] = '127.0.0.1:9001'
+
         channel = channel_factory.create_channel(channel_name)
         if channel_name in ['wx','wxy']:
             PluginManager().load_plugins()

channel/chat_channel.py

@@ -98,11 +98,12 @@ class ChatChannel(Channel):
             else:
                 context.type = ContextType.TEXT
             context.content = content
+            if 'desire_rtype' not in context and conf().get('always_reply_voice'):
+                context['desire_rtype'] = ReplyType.VOICE
         elif context.type == ContextType.VOICE: 
             if 'desire_rtype' not in context and conf().get('voice_reply_voice'):
                 context['desire_rtype'] = ReplyType.VOICE
 
-
         return context
 
     # 处理消息 TODO: 如果wechaty解耦，此处逻辑可以放置到父类
@@ -194,14 +195,17 @@ class ChatChannel(Channel):
                 'channel': self, 'context': context, 'reply': reply}))
             reply = e_context['reply']
             if not e_context.is_pass() and reply and reply.type:
-                logger.debug('[WX] ready to send reply: {} to {}'.format(reply, context))
+                logger.debug('[WX] ready to send reply: {}, context: {}'.format(reply, context))
                 self._send(reply, context)
 
     def _send(self, reply: Reply, context: Context, retry_cnt = 0):
         try:
             self.send(reply, context)
         except Exception as e:
-            logger.error('[WX] sendMsg error: {}'.format(e))
+            logger.error('[WX] sendMsg error: {}'.format(str(e)))
+            if isinstance(e, NotImplementedError):
+                return
+            logger.exception(e)
             if retry_cnt < 2:
                 time.sleep(3+3*retry_cnt)
                 self._send(reply, context, retry_cnt+1)

channel/wechat/wechat_channel.py

@@ -64,6 +64,23 @@ def _check(func):
         return func(self, cmsg)
     return wrapper
 
+#可用的二维码生成接口
+#https://api.qrserver.com/v1/create-qr-code/?size=400×400&data=https://www.abc.com
+#https://api.isoyu.com/qr/?m=1&e=L&p=20&url=https://www.abc.com
+def qrCallback(uuid,status,qrcode):
+    # logger.debug("qrCallback: {} {}".format(uuid,status))
+    if status == '0':
+        import qrcode
+        url = f"https://login.weixin.qq.com/l/{uuid}"
+
+        qr_api="https://api.isoyu.com/qr/?m=1&e=L&p=20&url={}".format(url)
+        print("You can also scan QRCode in the website below:\n{}".format(qr_api))
+        
+        qr = qrcode.QRCode(border=1)
+        qr.add_data(url)
+        qr.make(fit=True)
+        qr.print_ascii(invert=True)
+
 @singleton
 class WechatChannel(ChatChannel):
     def __init__(self):
@@ -76,13 +93,13 @@ class WechatChannel(ChatChannel):
         # login by scan QRCode
         hotReload = conf().get('hot_reload', False)
         try:
-            itchat.auto_login(enableCmdQR=2, hotReload=hotReload)
+            itchat.auto_login(enableCmdQR=2, hotReload=hotReload, qrCallback=qrCallback)
         except Exception as e:
             if hotReload:
                 logger.error("Hot reload failed, try to login without hot reload")
                 itchat.logout()
                 os.remove("itchat.pkl")
-                itchat.auto_login(enableCmdQR=2, hotReload=hotReload)
+                itchat.auto_login(enableCmdQR=2, hotReload=hotReload, qrCallback=qrCallback)
             else:
                 raise e
         self.user_id = itchat.instance.storageClass.userName

channel/wechat/wechaty_channel.py

@@ -20,7 +20,7 @@ from channel.wechat.wechaty_message import WechatyMessage
 from common.log import logger
 from config import conf
 try:
-    from voice.audio_convert import mp3_to_sil
+    from voice.audio_convert import any_to_sil
 except Exception as e:
     pass
 
@@ -35,14 +35,12 @@ class WechatyChannel(ChatChannel):
         pass
 
     def startup(self):
-        asyncio.run(self.main())
-
-    async def main(self):
         config = conf()
         token = config.get('wechaty_puppet_service_token')
         os.environ['WECHATY_PUPPET_SERVICE_TOKEN'] = token
-        os.environ['WECHATY_LOG']="warn"
-        # os.environ['WECHATY_PUPPET_SERVICE_ENDPOINT'] = '127.0.0.1:9001'
+        asyncio.run(self.main())
+
+    async def main(self):
         self.bot = Wechaty()
         self.bot.on('login', self.on_login)
         self.bot.on('message', self.on_message)
@@ -72,18 +70,9 @@ class WechatyChannel(ChatChannel):
             logger.info('[WX] sendMsg={}, receiver={}'.format(reply, receiver))
         elif reply.type == ReplyType.VOICE:
             voiceLength = None
-            if reply.content.endswith('.mp3'):
-                mp3_file = reply.content
-                sil_file = os.path.splitext(mp3_file)[0] + '.sil'
-                voiceLength = mp3_to_sil(mp3_file, sil_file)
-                try:
-                    os.remove(mp3_file)
-                except Exception as e:
-                    pass
-            elif reply.content.endswith('.sil'):
-                sil_file = reply.content
-            else:
-                raise Exception('voice file must be mp3 or sil format')
+            file_path = reply.content
+            sil_file = os.path.splitext(file_path)[0] + '.sil'
+            voiceLength = int(any_to_sil(file_path, sil_file))
             # 发送语音
             t = int(time.time())
             msg = FileBox.from_file(sil_file, name=str(t) + '.sil')
@@ -91,6 +80,7 @@ class WechatyChannel(ChatChannel):
                 msg.metadata['voiceLength'] = voiceLength
             asyncio.run_coroutine_threadsafe(receiver.say(msg),loop).result()
             try:
+                os.remove(file_path)
                 os.remove(sil_file)
             except Exception as e:
                 pass

config.py

@@ -47,16 +47,21 @@ available_setting = {
     "speech_recognition": False,  # 是否开启语音识别
     "group_speech_recognition": False,  # 是否开启群组语音识别
     "voice_reply_voice": False,  # 是否使用语音回复语音，需要设置对应语音合成引擎的api key
-    "voice_to_text": "openai",  # 语音识别引擎，支持openai,google
-    "text_to_voice": "baidu",  # 语音合成引擎，支持baidu,google,pytts(offline)
+    "always_reply_voice": False,  # 是否一直使用语音回复
+    "voice_to_text": "openai",  # 语音识别引擎，支持openai,google,azure
+    "text_to_voice": "baidu",  # 语音合成引擎，支持baidu,google,pytts(offline),azure
 
-    # baidu api的配置， 使用百度语音识别和语音合成时需要
+    # baidu 语音api配置， 使用百度语音识别和语音合成时需要
     "baidu_app_id": "",
     "baidu_api_key": "",
     "baidu_secret_key": "",
     # 1536普通话(支持简单的英文识别) 1737英语 1637粤语 1837四川话 1936普通话远场
     "baidu_dev_pid": "1536",
 
+    # azure 语音api配置， 使用azure语音识别和语音合成时需要
+    "azure_voice_api_key": "",
+    "azure_voice_region": "japaneast",
+
     # 服务时间限制，目前支持itchat
     "chat_time_module": False,  # 是否开启服务时间限制
     "chat_start_time": "00:00",  # 服务开始时间

docker/Dockerfile.debian.latest

@@ -0,0 +1,32 @@
+FROM python:3.10-slim
+
+LABEL maintainer="foo@bar.com"
+ARG TZ='Asia/Shanghai'
+
+ARG CHATGPT_ON_WECHAT_VER
+
+ENV BUILD_PREFIX=/app
+
+ADD . ${BUILD_PREFIX}
+
+RUN apt-get update \
+    &&apt-get install -y --no-install-recommends  bash \
+    ffmpeg espeak \
+    && cd ${BUILD_PREFIX} \
+    && cp config-template.json config.json \
+    && /usr/local/bin/python -m pip install --no-cache --upgrade pip \
+    && pip install --no-cache -r requirements.txt \
+    && pip install azure-cognitiveservices-speech
+    
+WORKDIR ${BUILD_PREFIX}
+
+ADD docker/entrypoint.sh /entrypoint.sh
+
+RUN chmod +x /entrypoint.sh \
+    && groupadd -r noroot \
+    && useradd -r -g noroot -s /bin/bash -d /home/noroot noroot \
+    && chown -R noroot:noroot ${BUILD_PREFIX}
+
+USER noroot
+
+ENTRYPOINT ["docker/entrypoint.sh"]

docker/build.latest.sh

@@ -1,4 +1,4 @@
 #!/bin/bash
 
-cd .. && docker build -f Dockerfile \
+cd .. && docker build -f docker/Dockerfile.latest \
              -t zhayujie/chatgpt-on-wechat .

plugins/README.md

@@ -1,6 +1,6 @@
 ## 插件化初衷
 
-之前未插件化的代码耦合程度高，如果要定制一些个性化功能（如流量控制、接入`NovelAI`画图平台等），需要了解代码主体，避免影响到其他的功能。在实现多个功能后，不但无法调整功能的优先级顺序，功能的配置项也会变得非常混乱。
+之前未插件化的代码耦合程度高，如果要定制一些个性化功能（如流量控制、接入`NovelAI`画图平台等），需要了解代码主体，避免影响到其他的功能。多个功能同时存在时，无法调整功能的优先级顺序，功能配置项也非常混乱。
 
 此时插件化应声而出。
 
@@ -11,7 +11,7 @@
 - [x] 插件化能够自由开关和调整优先级。
 - [x] 每个插件可在插件文件夹内维护独立的配置文件，方便代码的测试和调试，可以在独立的仓库开发插件。
 
-PS: 插件目前仅支持`itchat`
+PS: 插件目前支持`itchat`和`wechaty`
 
 ## 插件化实现
 

requirements.txt

@@ -7,6 +7,7 @@ PyQRCode>=1.2.1
 pysilk>=0.0.1
 pysilk_mod>=1.6.0
 pyttsx3>=2.90
+qrcode>=7.4.2
 requests>=2.28.2
 webuiapi>=0.6.2
 wechaty>=0.10.7

voice/audio_convert.py

@@ -1,7 +1,23 @@
+import shutil
 import wave
 import pysilk
 from pydub import AudioSegment
 
+sil_supports=[8000, 12000, 16000, 24000, 32000, 44100, 48000] # slk转wav时，支持的采样率
+def find_closest_sil_supports(sample_rate):
+    """
+    找到最接近的支持的采样率
+    """
+    if sample_rate in sil_supports:
+        return sample_rate
+    closest = 0
+    mindiff = 9999999
+    for rate in sil_supports:
+        diff = abs(rate - sample_rate)
+        if diff < mindiff:
+            closest = rate
+            mindiff = diff
+    return closest
 
 def get_pcm_from_wav(wav_path):
     """
@@ -13,6 +29,30 @@ def get_pcm_from_wav(wav_path):
     wav = wave.open(wav_path, "rb")
     return wav.readframes(wav.getnframes())
 
+def any_to_wav(any_path, wav_path):
+    """
+    把任意格式转成wav文件
+    """
+    if any_path.endswith('.wav'):
+        shutil.copy2(any_path, wav_path)
+        return
+    if any_path.endswith('.sil') or any_path.endswith('.silk') or any_path.endswith('.slk'):
+        return sil_to_wav(any_path, wav_path)
+    audio = AudioSegment.from_file(any_path)
+    audio.export(wav_path, format="wav")
+
+def any_to_sil(any_path, sil_path):
+    """
+    把任意格式转成sil文件
+    """
+    if any_path.endswith('.sil') or any_path.endswith('.silk') or any_path.endswith('.slk'):
+        shutil.copy2(any_path, sil_path)
+        return 10000
+    if any_path.endswith('.wav'):
+        return pcm_to_sil(any_path, sil_path)
+    if any_path.endswith('.mp3'):
+        return mp3_to_sil(any_path, sil_path)
+    raise NotImplementedError("Not support file type: {}".format(any_path))
 
 def mp3_to_wav(mp3_path, wav_path):
     """
@@ -21,26 +61,16 @@ def mp3_to_wav(mp3_path, wav_path):
     audio = AudioSegment.from_mp3(mp3_path)
     audio.export(wav_path, format="wav")
 
-def any_to_wav(any_path, wav_path):
-    """
-    把任意格式转成wav文件
-    """
-    if any_path.endswith('.wav'):
-        return
-    if any_path.endswith('.sil') or any_path.endswith('.silk') or any_path.endswith('.slk'):
-        return sil_to_wav(any_path, wav_path)
-    audio = AudioSegment.from_file(any_path)
-    audio.export(wav_path, format="wav")
-
-def pcm_to_silk(pcm_path, silk_path):
+def pcm_to_sil(pcm_path, silk_path):
     """
     wav 文件转成 silk
     return 声音长度，毫秒
     """
     audio = AudioSegment.from_wav(pcm_path)
     wav_data = audio.raw_data
+    rate = find_closest_sil_supports(audio.frame_rate)
     silk_data = pysilk.encode(
-        wav_data, data_rate=audio.frame_rate, sample_rate=audio.frame_rate)
+        wav_data, data_rate=rate, sample_rate=rate)
     with open(silk_path, "wb") as f:
         f.write(silk_data)
     return audio.duration_seconds * 1000
@@ -53,14 +83,13 @@ def mp3_to_sil(mp3_path, silk_path):
     """
     audio = AudioSegment.from_mp3(mp3_path)
     wav_data = audio.raw_data
-    silk_data = pysilk.encode(
-        wav_data, data_rate=audio.frame_rate, sample_rate=audio.frame_rate)
+    rate = find_closest_sil_supports(audio.frame_rate)
+    silk_data = pysilk.encode(wav_data, data_rate=rate, sample_rate=rate)
     # Save the silk file
     with open(silk_path, "wb") as f:
         f.write(silk_data)
     return audio.duration_seconds * 1000
 
-
 def sil_to_wav(silk_path, wav_path, rate: int = 24000):
     """
     silk 文件转 wav

voice/azure/azure_voice.py

@@ -0,0 +1,68 @@
+
+"""
+azure voice service
+"""
+import json
+import os
+import time
+import azure.cognitiveservices.speech as speechsdk
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from common.tmp_dir import TmpDir
+from voice.voice import Voice
+from config import conf
+"""
+Azure voice
+主目录设置文件中需填写azure_voice_api_key和azure_voice_region
+
+查看可用的 voice： https://speech.microsoft.com/portal/voicegallery
+
+"""
+
+class AzureVoice(Voice):
+
+    def __init__(self):
+        try:
+            curdir = os.path.dirname(__file__)
+            config_path = os.path.join(curdir, "config.json")
+            config = None
+            if not os.path.exists(config_path): #如果没有配置文件，创建本地配置文件
+                config = { "speech_synthesis_voice_name": "zh-CN-XiaoxiaoNeural", "speech_recognition_language": "zh-CN"}
+                with open(config_path, "w") as fw:
+                    json.dump(config, fw, indent=4)
+            else:
+                with open(config_path, "r") as fr:
+                    config = json.load(fr)
+            self.api_key = conf().get('azure_voice_api_key')
+            self.api_region = conf().get('azure_voice_region')
+            self.speech_config = speechsdk.SpeechConfig(subscription=self.api_key, region=self.api_region)
+            self.speech_config.speech_synthesis_voice_name = config["speech_synthesis_voice_name"]
+            self.speech_config.speech_recognition_language = config["speech_recognition_language"]
+        except Exception as e:
+            logger.warn("AzureVoice init failed: %s, ignore " % e)
+
+    def voiceToText(self, voice_file):
+        audio_config = speechsdk.AudioConfig(filename=voice_file)
+        speech_recognizer = speechsdk.SpeechRecognizer(speech_config=self.speech_config, audio_config=audio_config)
+        result = speech_recognizer.recognize_once()
+        if result.reason == speechsdk.ResultReason.RecognizedSpeech:
+            logger.info('[Azure] voiceToText voice file name={} text={}'.format(voice_file, result.text))
+            reply = Reply(ReplyType.TEXT, result.text)
+        else:
+            logger.error('[Azure] voiceToText error, result={}'.format(result))
+            reply = Reply(ReplyType.ERROR, "抱歉，语音识别失败")
+        return reply
+
+    def textToVoice(self, text):
+        fileName = TmpDir().path() + '语音回复_' + str(int(time.time())) + '.wav'
+        audio_config = speechsdk.AudioConfig(filename=fileName)
+        speech_synthesizer = speechsdk.SpeechSynthesizer(speech_config=self.speech_config, audio_config=audio_config)
+        result = speech_synthesizer.speak_text(text)
+        if result.reason == speechsdk.ResultReason.SynthesizingAudioCompleted:
+            logger.info(
+                '[Azure] textToVoice text={} voice file name={}'.format(text, fileName))
+            reply = Reply(ReplyType.VOICE, fileName)
+        else:
+            logger.error('[Azure] textToVoice error, result={}'.format(result))
+            reply = Reply(ReplyType.ERROR, "抱歉，语音合成失败")
+        return reply

voice/azure/config.json.template

@@ -0,0 +1,4 @@
+{
+    "speech_synthesis_voice_name": "zh-CN-XiaoxiaoNeural",
+    "speech_recognition_language": "zh-CN"
+}

voice/pytts/pytts_voice.py

@@ -25,12 +25,12 @@ class PyttsVoice(Voice):
 
     def textToVoice(self, text):
         try:
-            mp3File = TmpDir().path() + '语音回复_' + str(int(time.time())) + '.mp3'
-            self.engine.save_to_file(text, mp3File)
+            wavFile = TmpDir().path() + '语音回复_' + str(int(time.time())) + '.wav'
+            self.engine.save_to_file(text, wavFile)
             self.engine.runAndWait()
             logger.info(
-                '[Pytts] textToVoice text={} voice file name={}'.format(text, mp3File))
-            reply = Reply(ReplyType.VOICE, mp3File)
+                '[Pytts] textToVoice text={} voice file name={}'.format(text, wavFile))
+            reply = Reply(ReplyType.VOICE, wavFile)
         except Exception as e:
             reply = Reply(ReplyType.ERROR, str(e))
         finally:

voice/voice_factory.py

@@ -20,4 +20,7 @@ def create_voice(voice_type):
     elif voice_type == 'pytts':
         from voice.pytts.pytts_voice import PyttsVoice
         return PyttsVoice()
+    elif voice_type == 'azure':
+        from voice.azure.azure_voice import AzureVoice
+        return AzureVoice()
     raise RuntimeError