`bash OS/01/start.sh`

OS/01/assistant/conversations/user.json

@@ -1 +1 @@
-[{"role": "user", "type": "message", "content": "Disgusting.\n"}]
+[{"role": "user", "type": "message", "content": "And it works really well.\n"}]

OS/01/assistant/tts.py

@@ -19,9 +19,9 @@ def tts(text):
     with tempfile.NamedTemporaryFile() as temp_file:
         response.stream_to_file(temp_file.name)
         
-        # audio = AudioSegment.from_file(temp_file.name, format="mp3")
+        audio = AudioSegment.from_file(temp_file.name, format="mp3")
-        # # Gradual fade in and out over 0.2 seconds
+        # Gradual fade in and out over 0.2 seconds
-        # audio = audio.fade_in(200).fade_out(200)
+        audio = audio.fade_in(200).fade_out(200)
-        # play(audio)
+        play(audio)
         
         return temp_file.read()

OS/01/user/user.py

@@ -10,6 +10,9 @@ import websockets
 import queue
 import pydub
 import ast
+from pydub import AudioSegment
+from pydub.playback import play
+import io
 
 # Configuration for Audio Recording
 CHUNK = 1024  # Record in chunks of 1024 samples
@@ -109,7 +112,18 @@ async def websocket_communication(WS_URL):
 
                 async for message in websocket:
                     print(message)
-                    await asyncio.sleep(1)
+
+                    if message["type"] == "audio" and "content" in message:
+                        audio_bytes = bytes(ast.literal_eval(message["content"]))
+
+                        # Convert bytes to audio file
+                        audio_file = io.BytesIO(audio_bytes)
+                        audio = AudioSegment.from_mp3(audio_file)
+
+                        # Play the audio
+                        play(audio)
+
+                        await asyncio.sleep(1)
         except:
             print("Connecting...")
             await asyncio.sleep(2)