Docs changes, minor fixes

software/main.py

@@ -127,19 +127,21 @@ def run(
 
         if server == "light":
             light_server_port = server_port
+            light_server_host = server_host
             voice = True # The light server will support voice
         elif server == "livekit":
             # The light server should run at a different port if we want to run a livekit server
             spinner.stop()
-            print(f"Starting light server (required for livekit server) on the port before `--server-port` (port {server_port-1}), unless the `AN_OPEN_PORT` env var is set.")
+            print(f"Starting light server (required for livekit server) on localhost, on the port before `--server-port` (port {server_port-1}), unless the `AN_OPEN_PORT` env var is set.")
             print(f"The livekit server will be started on port {server_port}.")
             light_server_port = os.getenv('AN_OPEN_PORT', server_port-1)
+            light_server_host = "localhost"
             voice = False # The light server will NOT support voice. It will just run Open Interpreter. The Livekit server will handle voice
 
         server_thread = threading.Thread(
             target=start_server,
             args=(
-                server_host,
+                light_server_host,
                 light_server_port,
                 profile,
                 voice,

software/pyproject.toml

@@ -19,7 +19,7 @@ livekit-plugins-openai = "^0.8.1"
 livekit-plugins-silero = "^0.6.4"
 livekit-plugins-elevenlabs = "^0.7.3"
 segno = "^1.6.1"
-open-interpreter = {extras = ["os", "server"], version = "^0.3.9"}
+open-interpreter = {extras = ["os", "server"], version = "^0.3.10"}
 ngrok = "^1.4.0"
 realtimetts = {extras = ["all"], version = "^0.4.5"}
 realtimestt = "^0.2.41"

software/source/server/livekit/worker.py

@@ -16,8 +16,7 @@ async def entrypoint(ctx: JobContext):
     initial_ctx = ChatContext().append(
         role="system",
         text=(
-            "You are a voice assistant created by LiveKit. Your interface with users will be voice. "
+            "" # Open Interpreter handles this.
-            "You should use short and concise responses, and avoiding usage of unpronounceable punctuation."
         ),
     )
 
@@ -66,7 +65,9 @@ async def entrypoint(ctx: JobContext):
     await asyncio.sleep(1)
 
     # Greets the user with an initial message
-    await assistant.say("Hey, how can I help you today?", allow_interruptions=True)
+    await assistant.say("""Hi! You can hold the white circle below to speak to me.
+
+Try asking what I can do.""", allow_interruptions=True)
 
 
 if __name__ == "__main__":

software/source/server/server.py

@@ -2,12 +2,12 @@ from fastapi.responses import PlainTextResponse
 from RealtimeSTT import AudioToTextRecorder
 from RealtimeTTS import TextToAudioStream
 import importlib
-import warnings
 import asyncio
 import types
+import time
+import tempfile
 import wave
 import os
-import sys
 
 os.environ["INTERPRETER_REQUIRE_ACKNOWLEDGE"] = "False"
 os.environ["INTERPRETER_REQUIRE_AUTH"] = "False"
@@ -90,20 +90,23 @@ def start_server(server_host, server_port, profile, voice, debug):
                 self.stt.stop()
                 content = self.stt.text()
 
+                if False:
+                    audio_bytes = bytearray(b"".join(self.audio_chunks))
+                    with tempfile.NamedTemporaryFile(suffix='.wav', delete=False) as temp_file:
+                        with wave.open(temp_file.name, 'wb') as wav_file:
+                            wav_file.setnchannels(1)
+                            wav_file.setsampwidth(2)  # Assuming 16-bit audio
+                            wav_file.setframerate(16000)  # Assuming 16kHz sample rate
+                            wav_file.writeframes(audio_bytes)
+                        print(f"Audio for debugging: {temp_file.name}")
+                        time.sleep(10)
+                        
+
                 if content.strip() == "":
                     return
 
                 print(">", content.strip())
 
-                if False:
-                    audio_bytes = bytearray(b"".join(self.audio_chunks))
-                    with wave.open('audio.wav', 'wb') as wav_file:
-                        wav_file.setnchannels(1)
-                        wav_file.setsampwidth(2)  # Assuming 16-bit audio
-                        wav_file.setframerate(16000)  # Assuming 16kHz sample rate
-                        wav_file.writeframes(audio_bytes)
-                    print(os.path.abspath('audio.wav'))
-
                 await old_input({"role": "user", "type": "message", "content": content})
                 await old_input({"role": "user", "type": "message", "end": True})