Removed print statements, better audio playback

software/poetry.lock

@@ -2243,13 +2243,13 @@ socks = ["socksio (==1.*)"]
 
 [[package]]
 name = "huggingface-hub"
-version = "0.23.4"
+version = "0.23.5"
 description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub"
 optional = false
 python-versions = ">=3.8.0"
 files = [
-    {file = "huggingface_hub-0.23.4-py3-none-any.whl", hash = "sha256:3a0b957aa87150addf0cc7bd71b4d954b78e749850e1e7fb29ebbd2db64ca037"},
+    {file = "huggingface_hub-0.23.5-py3-none-any.whl", hash = "sha256:d7a7d337615e11a45cc14a0ce5a605db6b038dc24af42866f731684825226e90"},
-    {file = "huggingface_hub-0.23.4.tar.gz", hash = "sha256:35d99016433900e44ae7efe1c209164a5a81dbbcd53a52f99c281dcd7ce22431"},
+    {file = "huggingface_hub-0.23.5.tar.gz", hash = "sha256:67a9caba79b71235be3752852ca27da86bd54311d2424ca8afdb8dda056edf98"},
 ]
 
 [package.dependencies]
@@ -3988,7 +3988,7 @@ server = ["fastapi (>=0.111.0,<0.112.0)", "janus (>=1.0.0,<2.0.0)", "uvicorn (>=
 type = "git"
 url = "https://github.com/OpenInterpreter/open-interpreter.git"
 reference = "development"
-resolved_reference = "3db7e4b2dd93f48e1761ccbd24cd2b5a7985b06f"
+resolved_reference = "59409c2ddccb1a8d457099de7e24021afcba9ad8"
 
 [[package]]
 name = "openai"
@@ -4032,10 +4032,10 @@ files = [
 [package.dependencies]
 numpy = [
     {version = ">=1.21.0", markers = "python_version == \"3.9\" and platform_system == \"Darwin\" and platform_machine == \"arm64\""},
-    {version = ">=1.23.5", markers = "python_version >= \"3.11\""},
     {version = ">=1.21.4", markers = "python_version >= \"3.10\" and platform_system == \"Darwin\" and python_version < \"3.11\""},
     {version = ">=1.21.2", markers = "platform_system != \"Darwin\" and python_version >= \"3.10\" and python_version < \"3.11\""},
     {version = ">=1.19.3", markers = "platform_system == \"Linux\" and platform_machine == \"aarch64\" and python_version >= \"3.8\" and python_version < \"3.10\" or python_version > \"3.9\" and python_version < \"3.10\" or python_version >= \"3.9\" and platform_system != \"Darwin\" and python_version < \"3.10\" or python_version >= \"3.9\" and platform_machine != \"arm64\" and python_version < \"3.10\""},
+    {version = ">=1.23.5", markers = "python_version >= \"3.11\""},
 ]
 
 [[package]]

software/source/clients/base_device.py

@@ -3,6 +3,7 @@ import websockets
 import pyaudio
 from pynput import keyboard
 import json
+from yaspin import yaspin
 
 CHUNK = 1024
 FORMAT = pyaudio.paInt16
@@ -18,6 +19,8 @@ class Device:
         self.recording = False
         self.input_stream = None
         self.output_stream = None
+        self.spinner = yaspin()
+        self.play_audio = True
 
     async def connect_with_retry(self, max_retries=50, retry_delay=2):
         for attempt in range(max_retries):
@@ -26,7 +29,8 @@ class Device:
                 print("Connected to server.")
                 return
             except ConnectionRefusedError:
-                print(f"Waiting for the server to be ready. Retrying in {retry_delay} seconds...")
+                if attempt % 4 == 0:
+                    print(f"Waiting for the server to be ready...")
                 await asyncio.sleep(retry_delay)
         raise Exception("Failed to connect to the server after multiple attempts")
 
@@ -37,7 +41,7 @@ class Device:
                 try:
                     # Send start flag
                     await self.websocket.send(json.dumps({"role": "user", "type": "audio", "format": "bytes.wav", "start": True}))
-                    print("Sending audio start message")
+                    #print("Sending audio start message")
                     
                     while self.recording:
                         data = self.input_stream.read(CHUNK, exception_on_overflow=False)
@@ -45,7 +49,7 @@ class Device:
                     
                     # Send stop flag
                     await self.websocket.send(json.dumps({"role": "user", "type": "audio", "format": "bytes.wav", "end": True}))
-                    print("Sending audio end message")
+                    #print("Sending audio end message")
                 except Exception as e:
                     print(f"Error in send_audio: {e}")
             await asyncio.sleep(0.01)
@@ -56,26 +60,30 @@ class Device:
             try:
                 data = await self.websocket.recv()
                 if isinstance(data, bytes) and not self.recording:
-                    self.output_stream.write(data)
+                    if self.play_audio:
+                        self.output_stream.write(data)
             except Exception as e:
                 print(f"Error in receive_audio: {e}")
 
     def on_press(self, key):
         if key == keyboard.Key.space and not self.recording:
-            print("Space pressed, starting recording")
+            #print("Space pressed, starting recording")
+            print("\n")
+            self.spinner.start()
             self.recording = True
 
     def on_release(self, key):
         if key == keyboard.Key.space:
-            print("Space released, stopping recording")
+            self.spinner.stop()
+            #print("Space released, stopping recording")
             self.recording = False
-        elif key == keyboard.Key.esc:
+        # elif key == keyboard.Key.esc:
-            print("Esc pressed, stopping the program")
+        #     print("Esc pressed, stopping the program")
-            return False
+        #     return False
 
     async def main(self):
         await self.connect_with_retry()
-        print("Hold spacebar to record. Press 'Esc' to quit.")
+        print("Hold spacebar to record. Press 'CTRL-C' to quit.")
         listener = keyboard.Listener(on_press=self.on_press, on_release=self.on_release)
         listener.start()
         await asyncio.gather(self.send_audio(), self.receive_audio())

software/source/clients/mac/device.py

@@ -3,9 +3,10 @@ from ..base_device import Device
 device = Device()
 
 
-def main(server_url, debug):
+def main(server_url, debug, play_audio):
     device.server_url = server_url
     device.debug = debug
+    device.play_audio = play_audio
     device.start()
 
 

software/source/server/async_server.py

@@ -10,7 +10,7 @@ import wave
 import asyncio
 from fastapi.responses import PlainTextResponse
 
-def start_server(server_host, server_port, profile, debug):
+def start_server(server_host, server_port, profile, debug, play_audio):
 
     # Load the profile module from the provided path
     spec = importlib.util.spec_from_file_location("profile", profile)
@@ -47,6 +47,8 @@ def start_server(server_host, server_port, profile, debug):
     interpreter.server.host = server_host
     interpreter.server.port = server_port
 
+    interpreter.play_audio = play_audio
+
 
     interpreter.audio_chunks = []
 
@@ -100,12 +102,12 @@ def start_server(server_host, server_port, profile, debug):
             if output["type"] == "message" and len(output.get("content", "")) > 0:
                 self.tts.feed(output.get("content"))
                 if not self.tts.is_playing() and any([c in delimiters for c in output.get("content")]): # Start playing once the first delimiter is encountered.
-                    self.tts.play_async(on_audio_chunk=self.on_tts_chunk, muted=True, sentence_fragment_delimiters=delimiters)
+                    self.tts.play_async(on_audio_chunk=self.on_tts_chunk, muted=not self.play_audio, sentence_fragment_delimiters=delimiters)
                     return {"role": "assistant", "type": "audio", "format": "bytes.wav", "start": True}
 
             if output == {"role": "assistant", "type": "message", "end": True}:
                 if not self.tts.is_playing(): # We put this here in case it never outputs a delimiter and never triggers play_async^
-                    self.tts.play_async(on_audio_chunk=self.on_tts_chunk, muted=True, sentence_fragment_delimiters=delimiters)
+                    self.tts.play_async(on_audio_chunk=self.on_tts_chunk, muted=not self.play_audio, sentence_fragment_delimiters=delimiters)
                     return {"role": "assistant", "type": "audio", "format": "bytes.wav", "start": True}
                 return {"role": "assistant", "type": "audio", "format": "bytes.wav", "end": True}
 

software/start.py

@@ -134,6 +134,11 @@ def _run(
     signal.signal(signal.SIGINT, handle_exit)
 
     if server:
+        # Have the server play audio if we're running this on the same device. Needless pops and clicks otherwise!
+        if client:
+            play_audio = True
+        else:
+            play_audio = False
         server_thread = threading.Thread(
             target=start_server,
             args=(
@@ -141,6 +146,7 @@ def _run(
                 server_port,
                 profile,
                 debug,
+                play_audio,
             ),
         )
         server_thread.start()
@@ -172,7 +178,13 @@ def _run(
             f".clients.{client_type}.device", package="source"
         )
 
-        client_thread = threading.Thread(target=module.main, args=[server_url, debug])
+        # Have the server play audio if we're running this on the same device. Needless pops and clicks otherwise!
+        if server:
+            play_audio = False
+        else:
+            play_audio = True
+
+        client_thread = threading.Thread(target=module.main, args=[server_url, debug, play_audio])
         client_thread.start()
 
     try: