feat: new voice class pytts

voice/google/google_voice.py

@@ -5,7 +5,6 @@ google voice service
 
 import time
 import speech_recognition
-import pyttsx3
 from gtts import gTTS
 from bridge.reply import Reply, ReplyType
 from common.log import logger
@@ -15,21 +14,11 @@ from voice.voice import Voice
 
 class GoogleVoice(Voice):
     recognizer = speech_recognition.Recognizer()
-    engine = pyttsx3.init()
 
     def __init__(self):
-        # 语速
-        self.engine.setProperty('rate', 125)
-        # 音量
-        self.engine.setProperty('volume', 1.0)
-        # 0为男声，1为女声
-        voices = self.engine.getProperty('voices')
-        self.engine.setProperty('voice', voices[1].id)
+        pass
 
     def voiceToText(self, voice_file):
-        # new_file = voice_file.replace('.mp3', '.wav')
-        # subprocess.call('ffmpeg -i ' + voice_file +
-        #                 ' -acodec pcm_s16le -ac 1 -ar 16000 ' + new_file, shell=True)
         with speech_recognition.AudioFile(voice_file) as source:
             audio = self.recognizer.record(source)
         try:
@@ -46,8 +35,6 @@ class GoogleVoice(Voice):
     def textToVoice(self, text):
         try:
             mp3File = TmpDir().path() + '语音回复_' + str(int(time.time())) + '.mp3'
-            # self.engine.save_to_file(text, textFile)
-            # self.engine.runAndWait()
             tts = gTTS(text=text, lang='zh')
             tts.save(mp3File)            
             logger.info(

voice/openai/openai_voice.py

@@ -28,6 +28,3 @@ class OpenaiVoice(Voice):
             reply = Reply(ReplyType.ERROR, str(e))
         finally:
             return reply
-
-    def textToVoice(self, text):
-        pass

voice/pytts/pytts_voice.py

@@ -0,0 +1,37 @@
+
+"""
+pytts voice service (offline)
+"""
+
+import time
+import pyttsx3
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from common.tmp_dir import TmpDir
+from voice.voice import Voice
+
+
+class PyttsVoice(Voice):
+    engine = pyttsx3.init()
+
+    def __init__(self):
+        # 语速
+        self.engine.setProperty('rate', 125)
+        # 音量
+        self.engine.setProperty('volume', 1.0)
+        for voice in self.engine.getProperty('voices'):
+            if "Chinese" in voice.name:
+                self.engine.setProperty('voice', voice.id)
+
+    def textToVoice(self, text):
+        try:
+            mp3File = TmpDir().path() + '语音回复_' + str(int(time.time())) + '.mp3'
+            self.engine.save_to_file(text, mp3File)
+            self.engine.runAndWait()
+            logger.info(
+                '[Pytts] textToVoice text={} voice file name={}'.format(text, mp3File))
+            reply = Reply(ReplyType.VOICE, mp3File)
+        except Exception as e:
+            reply = Reply(ReplyType.ERROR, str(e))
+        finally:
+            return reply

voice/voice_factory.py

@@ -17,4 +17,7 @@ def create_voice(voice_type):
     elif voice_type == 'openai':
         from voice.openai.openai_voice import OpenaiVoice
         return OpenaiVoice()
+    elif voice_type == 'pytts':
+        from voice.pytts.pytts_voice import PyttsVoice
+        return PyttsVoice()
     raise RuntimeError