fix(real-time-voicebot): use env vars for API keys

real-time-voicebot/.env.example

@@ -0,0 +1,3 @@
+ASSEMBLYAI_API_KEY=your_assemblyai_api_key
+OPENAI_API_KEY=your_openai_api_key
+ELEVENLABS_API_KEY=your_elevenlabs_api_key

real-time-voicebot/README.md

@@ -20,11 +20,16 @@ Before running the application, you need API keys for the following services:
 - [Get the API key for OpenAI here →](https://platform.openai.com/api-keys)
 - [Get the API key for ElevenLabs here →](https://elevenlabs.io/app/sign-in)
 
-Update the API keys in the code by replacing the placeholders in the `AI_Assistant` class.
+Copy `.env.example` to `.env` and add your API keys:
+
+```bash
+cp .env.example .env
+```
 
 ## Run the application
 
 ```bash
+pip install assemblyai openai elevenlabs python-dotenv
 python app.py
 ```
 ---
@@ -36,5 +41,3 @@ python app.py
 
 ## Contribution
 Contributions are welcome! Please fork the repository and submit a pull request with your improvements.
-
-

real-time-voicebot/app.py

@@ -1,20 +1,20 @@
+import os
+from dotenv import load_dotenv
 import assemblyai as aai
 from elevenlabs import stream
 from elevenlabs.client import ElevenLabs
 from openai import OpenAI
 
+load_dotenv()
+
 class AI_Assistant:
     def __init__(self):
-        aai.settings.api_key = "<AssemblyAI API Key>"
-        self.openai_client = OpenAI(api_key = "<OpenAI API Key>")
-        self.elevenlabs_api_key = "<ElevenLabs API Key>"
-
-        self.elevenlabs_client = ElevenLabs(api_key = self.elevenlabs_api_key)
-
+        aai.settings.api_key = os.getenv("ASSEMBLYAI_API_KEY")
+        self.openai_client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
+        self.elevenlabs_client = ElevenLabs(api_key=os.getenv("ELEVENLABS_API_KEY"))
         self.transcriber = None
-
         self.interaction = [
-            {"role":"system", "content":"You are a helpful travel guide in London, UK, helping a tourist plan their trip. Be conversational and concise in your responses."},
+            {"role": "system", "content": "You are a helpful travel guide in London, UK, helping a tourist plan their trip. Be conversational and concise in your responses."},
         ]
 
     def stop_transcription(self):
@@ -24,15 +24,12 @@ def stop_transcription(self):
 
     def on_open(self, session_opened: aai.RealtimeSessionOpened):
         print("Session ID:", session_opened.session_id)
-        return
 
     def on_error(self, error: aai.RealtimeError):
         print("An error occured:", error)
-        return
 
     def on_close(self):
         print("Closing Session")
-        return
 
     def on_data(self, transcript: aai.RealtimeTranscript):
         if not transcript.text:
@@ -44,52 +41,43 @@ def on_data(self, transcript: aai.RealtimeTranscript):
 
     def start_transcription(self):
         self.transcriber = aai.RealtimeTranscriber(
-            sample_rate = 16000,
-            on_data = self.on_data,
-            on_error = self.on_error,
-            on_open = self.on_open,
-            on_close = self.on_close,
-            end_utterance_silence_threshold = 1000
+            sample_rate=16000,
+            on_data=self.on_data,
+            on_error=self.on_error,
+            on_open=self.on_open,
+            on_close=self.on_close,
+            end_utterance_silence_threshold=1000
         )
-
         self.transcriber.connect()
         microphone_stream = aai.extras.MicrophoneStream(sample_rate=16000)
         self.transcriber.stream(microphone_stream)
 
     def generate_ai_response(self, transcript):
-
         self.stop_transcription()
-
-        self.interaction.append({"role":"user", "content": transcript.text})
+        self.interaction.append({"role": "user", "content": transcript.text})
         print(f"\nTourist: {transcript.text}", end="\r\n")
 
         response = self.openai_client.chat.completions.create(
-            model = "gpt-3.5-turbo",
-            messages = self.interaction
+            model="gpt-3.5-turbo",
+            messages=self.interaction
         )
-
         ai_response = response.choices[0].message.content
-
         self.generate_audio(ai_response)
-
         self.start_transcription()
         print(f"\nReal-time transcription: ", end="\r\n")
 
-
     def generate_audio(self, text):
-
-        self.interaction.append({"role":"assistant", "content": text})
+        self.interaction.append({"role": "assistant", "content": text})
         print(f"\nAI Guide: {text}")
-
         audio_stream = self.elevenlabs_client.generate(
-            text = text,
-            voice = "Rachel",
-            stream = True
+            text=text,
+            voice="Rachel",
+            stream=True
         )
-
         stream(audio_stream)
 
+
 greeting = "Thank you for calling London Travel Guide. My name is Rachel, how may I assist you?"
 ai_assistant = AI_Assistant()
 ai_assistant.generate_audio(greeting)
-ai_assistant.start_transcription()
+ai_assistant.start_transcription()