fix: get correct audio format in pytts

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
@@ -13,6 +13,30 @@ 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):
     """
@@ -21,18 +45,7 @@ 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
@@ -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: