add logger

simple_turn_based_conversation.py

@@ -8,9 +8,11 @@ from vocode.turn_based.synthesizer.azure_synthesizer import AzureSynthesizer
 from vocode.turn_based.transcriber.whisper_transcriber import WhisperTranscriber
 from vocode.turn_based.turn_based_conversation import TurnBasedConversation
 
-load_dotenv()
-vocode.api_key = os.getenv("VOCODE_API_KEY")
+logging.basicConfig()
+logger = logging.getLogger(__name__)
+logger.setLevel(logging.INFO)
 
+load_dotenv()
 
 if __name__ == "__main__":
     microphone_input, speaker_output = create_microphone_input_and_speaker_output(
@@ -26,8 +28,14 @@ if __name__ == "__main__":
             initial_message="Hello!",
         ),
         synthesizer=AzureSynthesizer(sampling_rate=speaker_output.sampling_rate),
+        logger=logger,
     )
+    print("Starting conversation. Press Ctrl+C to exit.")
     while True:
+        try:
+            input("Press enter to start recording...")
             conversation.start_speech()
-        input("Press enter to end speech")
+            input("Press enter to end recording...")
             conversation.end_speech_and_respond()
+        except KeyboardInterrupt:
+            break

vocode/turn_based/turn_based_conversation.py

@@ -1,3 +1,4 @@
+import logging
 from vocode.turn_based.agent.base_agent import BaseAgent
 from vocode.turn_based.input_device.base_input_device import (
     BaseInputDevice,
@@ -15,6 +16,7 @@ class TurnBasedConversation:
         agent: BaseAgent,
         synthesizer: BaseSynthesizer,
         output_device: BaseOutputDevice,
+        logger: logging.Logger = None,
     ):
         self.input_device = input_device
         self.transcriber = transcriber
@@ -22,6 +24,7 @@ class TurnBasedConversation:
         self.synthesizer = synthesizer
         self.output_device = output_device
         self.maybe_play_initial_message()
+        self.logger = logger or logging.getLogger(__name__)
 
     def maybe_play_initial_message(self):
         if self.agent.initial_message:
@@ -34,5 +37,7 @@ class TurnBasedConversation:
 
     def end_speech_and_respond(self):
         human_input = self.transcriber.transcribe(self.input_device.end_listening())
+        self.logger.info(f"Transcription: {human_input}")
         agent_response = self.agent.respond(human_input)
+        self.logger.info(f"Agent response: {agent_response}")
         self.output_device.send_audio(self.synthesizer.synthesize(agent_response))