Add OpenRouter support

README.md

@@ -224,6 +224,7 @@ If you are running LLM locally via [Ollama](https://ollama.com/), make sure the
 
 - **OpenAI**: Uses OpenAI's GPT-4 model.
 - **Groq**: Uses Groq's LLaMA model.
+- **OpenRouter**: Uses any model available on OpenRouter (default: Gemini 2.0 Flash).
 - **Ollama**: Uses any model served via Ollama.
 - **Local**: Placeholder for a local language model.
 

voice_assistant/api_key_manager.py

@@ -10,7 +10,8 @@
     },
     "response":{
         "openai":Config.OPENAI_API_KEY,
-        "groq": Config.GROQ_API_KEY
+        "groq": Config.GROQ_API_KEY,
+        "openrouter": Config.OPENROUTER_API_KEY
     },
     "tts": {
         "openai": Config.OPENAI_API_KEY,

voice_assistant/config.py

@@ -22,7 +22,7 @@ class Config:
     """
     # Model selection
     TRANSCRIPTION_MODEL = 'deepgram'  # possible values: openai, groq, deepgram, fastwhisperapi
-    RESPONSE_MODEL = 'openai'  # possible values: openai, groq, ollama
+    RESPONSE_MODEL = 'openai'  # possible values: openai, groq, ollama, openrouter
     TTS_MODEL = 'openai'  # possible values: openai, deepgram, elevenlabs, melotts, cartesia, piper
 
     # Piper Server configuration
@@ -36,6 +36,7 @@ class Config:
     OLLAMA_LLM="llama3:8b"
     GROQ_LLM="llama3-8b-8192"
     OPENAI_LLM="gpt-4o"
+    OPENROUTER_LLM="google/gemini-2.0-flash-exp:free"
 
     # API keys and paths
     OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
@@ -44,6 +45,11 @@ class Config:
     ELEVENLABS_API_KEY = os.getenv("ELEVENLABS_API_KEY")
     LOCAL_MODEL_PATH = os.getenv("LOCAL_MODEL_PATH")
     CARTESIA_API_KEY = os.getenv("CARTESIA_API_KEY")
+<<<<<<< Updated upstream
+=======
+    GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
+    OPENROUTER_API_KEY = os.getenv("OPENROUTER_API_KEY")
+>>>>>>> Stashed changes
 
     # for serving the MeloTTS model
     TTS_PORT_LOCAL = 5150
@@ -62,7 +68,7 @@ def validate_config():
         Config._validate_model('TRANSCRIPTION_MODEL', [
             'openai', 'groq', 'deepgram', 'fastwhisperapi', 'local'])
         Config._validate_model('RESPONSE_MODEL', [
-            'openai', 'groq', 'ollama', 'local'])
+            'openai', 'groq', 'ollama', 'local', 'openrouter'])
         Config._validate_model('TTS_MODEL', [
             'openai', 'deepgram', 'elevenlabs', 'melotts', 'cartesia', 'local', 'piper'])
 
@@ -72,6 +78,7 @@ def validate_config():
 
         Config._validate_api_key('RESPONSE_MODEL', 'openai', 'OPENAI_API_KEY')
         Config._validate_api_key('RESPONSE_MODEL', 'groq', 'GROQ_API_KEY')
+        Config._validate_api_key('RESPONSE_MODEL', 'openrouter', 'OPENROUTER_API_KEY')
 
         Config._validate_api_key('TTS_MODEL', 'openai', 'OPENAI_API_KEY')
         Config._validate_api_key('TTS_MODEL', 'deepgram', 'DEEPGRAM_API_KEY')

voice_assistant/response_generation.py

@@ -27,6 +27,8 @@ def generate_response(model:str, api_key:str, chat_history:list, local_model_pat
             return _generate_openai_response(api_key, chat_history)
         elif model == 'groq':
             return _generate_groq_response(api_key, chat_history)
+        elif model == 'openrouter':
+            return _generate_openrouter_response(api_key, chat_history)
         elif model == 'ollama':
             return _generate_ollama_response(chat_history)
         elif model == 'local':
@@ -61,4 +63,15 @@ def _generate_ollama_response(chat_history):
         model=Config.OLLAMA_LLM,
         messages=chat_history,
     )
-    return response['message']['content']
+    return response['message']['content']
+
+def _generate_openrouter_response(api_key, chat_history):
+    client = OpenAI(
+        base_url="https://openrouter.ai/api/v1",
+        api_key=api_key,
+    )
+    response = client.chat.completions.create(
+        model=Config.OPENROUTER_LLM,
+        messages=chat_history,
+    )
+    return response.choices[0].message.content