fix: get correct audio format in pytts

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

@@ -194,14 +194,17 @@ 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/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 = 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

voice/audio_convert.py

@@ -1,8 +1,8 @@
+import shutil
 import wave
 import pysilk
 from pydub import AudioSegment
 
-
 def get_pcm_from_wav(wav_path):
     """
     从 wav 文件中读取 pcm
@@ -13,26 +13,39 @@ def get_pcm_from_wav(wav_path):
     wav = wave.open(wav_path, "rb")
     return wav.readframes(wav.getnframes())
 
-
-def mp3_to_wav(mp3_path, wav_path):
-    """
-    把mp3格式转成pcm文件
-    """
-    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'):
+        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 pcm_to_silk(pcm_path, silk_path):
+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):
+    """
+    把mp3格式转成pcm文件
+    """
+    audio = AudioSegment.from_mp3(mp3_path)
+    audio.export(wav_path, format="wav")
+
+def pcm_to_sil(pcm_path, silk_path):
     """
     wav 文件转成 silk
     return 声音长度，毫秒
@@ -60,7 +73,6 @@ def mp3_to_sil(mp3_path, silk_path):
         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

@@ -56,7 +56,7 @@ class AzureVoice(Voice):
         return reply
 
     def textToVoice(self, text):
-        fileName = TmpDir().path() + '语音回复_' + str(int(time.time())) + '.mp3'
+        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)

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: