update

Author: bcherry

src/agent.py

@@ -23,7 +23,7 @@
 class Assistant(Agent):
     def __init__(self) -> None:
         super().__init__(
-            instructions="""You are a helpful voice AI assistant.
+            instructions="""You are a helpful voice AI assistant. The user is interacting with you via voice, even if you perceive the conversation as text.
             You eagerly assist users with their questions by providing information from your extensive knowledge.
             Your responses are concise, to the point, and without any complex formatting or punctuation including emojis, asterisks, or other symbols.
             You are curious, friendly, and have a sense of humor.""",
@@ -62,13 +62,13 @@ async def entrypoint(ctx: JobContext):
     session = AgentSession(
         # Speech-to-text (STT) is your agent's ears, turning the user's speech into text that the LLM can understand
         # See all available models at https://docs.livekit.io/agents/models/stt/
-        stt="assemblyai/universal-streaming",
+        stt="assemblyai/universal-streaming:en",
         # A Large Language Model (LLM) is your agent's brain, processing user input and generating a response
         # See all available models at https://docs.livekit.io/agents/models/llm/
-        llm="azure/gpt-4o-mini",
+        llm="openai/gpt-4.1-mini",
         # Text-to-speech (TTS) is your agent's voice, turning the LLM's text into speech that the user can hear
         # See all available models as well as voice selections at https://docs.livekit.io/agents/models/tts/
-        tts="cartesia/sonic-2:f786b574-daa5-4673-aa0c-cbe3e8534c02",
+        tts="cartesia/sonic-2:9626c31c-bec5-4cca-baa8-f8ba9e84c8bc",
         # VAD and turn detection are used to determine when the user is speaking and when the agent should respond
         # See more at https://docs.livekit.io/agents/build/turns
         turn_detection=MultilingualModel(),

tests/test_agent.py

@@ -5,7 +5,7 @@
 
 
 def _llm() -> llm.LLM:
-    return inference.LLM(model="azure/gpt-4o-mini")
+    return inference.LLM(model="openai/gpt-4.1-mini")
 
 
 @pytest.mark.asyncio