msink

voice_recognition.py

@@ -46,8 +46,15 @@ class SRAudioSinkHammerVersion(AudioSink):
 
 class Transcriber(commands.Cog):
     def __init__(self, bot):
+        def callback(user, data: voice_recv.VoiceData):
+            logger.info(f"Got packet from {user}")
+
         self.bot = bot
         self._last_member = None
+        bsink = voice_recv.BasicSink(callback)
+        wsink = voice_recv.WaveSink(destination="/home/pi/Conjurer/wav.wav")
+        fsink = voice_recv.FFmpegSink(filename = ".home/pi/Conjurer/mp3.mp3")
+        self.sink_list = [bsink, wsink, fsink]
 
     async def transcribe():
         config = aai.TranscriptionConfig(speaker_labels=True)
@@ -61,22 +68,11 @@ class Transcriber(commands.Cog):
           print(f"Speaker {utterance.speaker}: {utterance.text}")
     @commands.hybrid_command(name="transcribe")
     async def test(self, ctx):
-        def callback(user, data: voice_recv.VoiceData):
-            logger.info(f"Got packet from {user}")
-
-            ## voice power level, how loud the user is speaking
-            # ext_data = packet.extension_data.get(voice_recv.ExtensionID.audio_power)
-            # value = int.from_bytes(ext_data, 'big')
-            # power = 127-(value & 127)
-            # print('#' * int(power * (79/128)))
-            ## instead of 79 you can use shutil.get_terminal_size().columns-1
         logger.info("Attempt transcribe")
         vc = await ctx.author.voice.channel.connect(cls=voice_recv.VoiceRecvClient)
         logger.info("Connected")
-        wsink = voice_recv.WaveSink(destination="/home/pi/Conjurer/Test.mp3")
+        msink = voice_recv.MultiAudioSink(destinations= self.sink_list)
-        fsink = voice_recv.FFmpegSink(filename="/home/pi/Conjurer/Test.mp3")
+        vc.listen(msink)
-
-        vc.listen(fsink)
 
 
     @commands.command(name="stop_transcribe")