api key configs

simple_turn_based_conversation.py

@@ -2,7 +2,6 @@ import logging
 from dotenv import load_dotenv
 import os
 from vocode.helpers import create_microphone_input_and_speaker_output
-import vocode
 from vocode.turn_based.agent.chat_gpt_agent import ChatGPTAgent
 from vocode.turn_based.synthesizer.azure_synthesizer import AzureSynthesizer
 from vocode.turn_based.transcriber.whisper_transcriber import WhisperTranscriber
@@ -22,12 +21,17 @@ if __name__ == "__main__":
     conversation = TurnBasedConversation(
         input_device=microphone_input,
         output_device=speaker_output,
-        transcriber=WhisperTranscriber(),
+        transcriber=WhisperTranscriber(api_key=os.getenv("OPENAI_API_KEY")),
         agent=ChatGPTAgent(
             system_prompt="The AI is having a pleasant conversation about life",
             initial_message="Hello!",
+            api_key=os.getenv("OPENAI_API_KEY"),
+        ),
+        synthesizer=AzureSynthesizer(
+            sampling_rate=speaker_output.sampling_rate,
+            api_key=os.getenv("AZURE_SPEECH_KEY"),
+            region=os.getenv("AZURE_SPEECH_REGION"),
         ),
-        synthesizer=AzureSynthesizer(sampling_rate=speaker_output.sampling_rate),
         logger=logger,
     )
     print("Starting conversation. Press Ctrl+C to exit.")

vocode/__init__.py

@@ -4,4 +4,4 @@ from dotenv import load_dotenv
 load_dotenv()
 
 api_key = os.getenv("VOCODE_API_KEY")
-base_url = os.getenv("VOCODE_BASE_URL", "api.vocode.dev")
+base_url = os.getenv("VOCODE_BASE_URL", "api.vocode.dev")

vocode/turn_based/agent/chat_gpt_agent.py

@@ -1,4 +1,6 @@
+import os
 from typing import Optional
+import openai
 from langchain.prompts import (
     ChatPromptTemplate,
     MessagesPlaceholder,
@@ -16,12 +18,16 @@ class ChatGPTAgent(BaseAgent):
     def __init__(
         self,
         system_prompt: str,
+        api_key: Optional[str] = None,
         initial_message: Optional[str] = None,
         model_name: str = "gpt-3.5-turbo",
         temperature: float = 0.7,
         max_tokens: int = 100,
     ):
         super().__init__(initial_message=initial_message)
+        openai.api_key = os.getenv("OPENAI_API_KET", api_key)
+        if not openai.api_key:
+            raise ValueError("OpenAI API key not provided")
         self.prompt = ChatPromptTemplate.from_messages(
             [
                 SystemMessagePromptTemplate.from_template(system_prompt),

vocode/turn_based/synthesizer/azure_synthesizer.py

@@ -1,19 +1,22 @@
 import os
-from dotenv import load_dotenv
+from typing import Optional
 import azure.cognitiveservices.speech as speechsdk
 from pydub import AudioSegment
 
 from vocode.turn_based.synthesizer.base_synthesizer import BaseSynthesizer
 
-load_dotenv()
-
 
 class AzureSynthesizer(BaseSynthesizer):
-    def __init__(self, sampling_rate: int):
+    def __init__(
+        self,
+        sampling_rate: int,
+        api_key: Optional[str] = None,
+        region: Optional[str] = None,
+    ):
         self.sampling_rate = sampling_rate
         speech_config = speechsdk.SpeechConfig(
-            subscription=os.environ.get("AZURE_SPEECH_KEY"),
-            region=os.environ.get("AZURE_SPEECH_REGION"),
+            subscription=os.getenv("AZURE_SPEECH_KEY", api_key),
+            region=os.getenv("AZURE_SPEECH_REGION", region),
         )
         if self.sampling_rate == 44100:
             speech_config.set_speech_synthesis_output_format(

vocode/turn_based/transcriber/whisper_transcriber.py

@@ -1,17 +1,18 @@
+from typing import Optional
 from pydub import AudioSegment
 import io
 import os
-from dotenv import load_dotenv
 import openai
 
 from vocode.turn_based.transcriber.base_transcriber import BaseTranscriber
 
-load_dotenv()
-
-openai.api_key = os.getenv("OPENAI_API_KEY")
-
 
 class WhisperTranscriber(BaseTranscriber):
+    def __init__(self, api_key: Optional[str] = None):
+        openai.api_key = os.getenv("OPENAI_API_KEY", api_key)
+        if not openai.api_key:
+            raise ValueError("OpenAI API key not provided")
+
     def transcribe(self, audio_segment: AudioSegment) -> str:
         in_memory_wav = io.BytesIO()
         audio_segment.export(in_memory_wav, format="wav")