Merge pull request #29 from livekit-examples/bcherry/sonic-3

Use sonic-3 by default

Author: bcherry

src/agent.py

@@ -10,6 +10,7 @@
     RoomInputOptions,
     WorkerOptions,
     cli,
+    inference,
     metrics,
 )
 from livekit.plugins import noise_cancellation, silero
@@ -62,13 +63,15 @@ 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:en",
+        stt=inference.STT(model="assemblyai/universal-streaming", language="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="openai/gpt-4.1-mini",
+        llm=inference.LLM(model="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-2:9626c31c-bec5-4cca-baa8-f8ba9e84c8bc",
+        tts=inference.TTS(
+            model="cartesia/sonic-3", voice="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(),