From 802cebdd0c095320405c097c9dec396b38d99949 Mon Sep 17 00:00:00 2001
From: Topherhindman <topher.hindman@livekit.io>
Date: Tue, 7 Apr 2026 15:47:56 -0700
Subject: [PATCH] Upgrade LLM model from GPT-4.1 to GPT-5.2 and aicoustics
 (#58)

* Upgrade LLM model from GPT-4.1 to GPT-5.2

* Switch noise cancellation to ai-coustics QUAIL_VF_L
---
 pyproject.toml | 1 +
 src/agent.py   | 8 +++++---
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/pyproject.toml b/pyproject.toml
index e3aeb6a..13315ce 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -10,6 +10,7 @@ requires-python = ">=3.10, <3.15"
 
 dependencies = [
     "livekit-agents[silero,turn-detector]~=1.4",
+    "livekit-plugins-ai-coustics",
     "livekit-plugins-noise-cancellation~=0.2",
     "python-dotenv",
 ]
diff --git a/src/agent.py b/src/agent.py
index fbc807a..605fc39 100644
--- a/src/agent.py
+++ b/src/agent.py
@@ -12,7 +12,7 @@ from livekit.agents import (
     inference,
     room_io,
 )
-from livekit.plugins import noise_cancellation, silero
+from livekit.plugins import ai_coustics, noise_cancellation, silero
 from livekit.plugins.turn_detector.multilingual import MultilingualModel
 
 logger = logging.getLogger("agent")
@@ -72,7 +72,7 @@ async def my_agent(ctx: JobContext):
         stt=inference.STT(model="deepgram/nova-3", language="multi"),
         # 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=inference.LLM(model="openai/gpt-4.1-mini"),
+        llm=inference.LLM(model="openai/gpt-5.2-chat-latest"),
         # 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=inference.TTS(
@@ -115,7 +115,9 @@ async def my_agent(ctx: JobContext):
                     noise_cancellation.BVCTelephony()
                     if params.participant.kind
                     == rtc.ParticipantKind.PARTICIPANT_KIND_SIP
-                    else noise_cancellation.BVC()
+                    else ai_coustics.audio_enhancement(
+                        model=ai_coustics.EnhancerModel.QUAIL_VF_L
+                    )
                 ),
             ),
         ),