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
This commit is contained in:
Topherhindman
2026-04-07 15:47:56 -07:00
committed by GitHub
parent 95bedcd581
commit 802cebdd0c
2 changed files with 6 additions and 3 deletions
+1
View File
@@ -10,6 +10,7 @@ requires-python = ">=3.10, <3.15"
dependencies = [ dependencies = [
"livekit-agents[silero,turn-detector]~=1.4", "livekit-agents[silero,turn-detector]~=1.4",
"livekit-plugins-ai-coustics",
"livekit-plugins-noise-cancellation~=0.2", "livekit-plugins-noise-cancellation~=0.2",
"python-dotenv", "python-dotenv",
] ]
+5 -3
View File
@@ -12,7 +12,7 @@ from livekit.agents import (
inference, inference,
room_io, 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 from livekit.plugins.turn_detector.multilingual import MultilingualModel
logger = logging.getLogger("agent") logger = logging.getLogger("agent")
@@ -72,7 +72,7 @@ async def my_agent(ctx: JobContext):
stt=inference.STT(model="deepgram/nova-3", language="multi"), 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 # 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/ # 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 # 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/ # See all available models as well as voice selections at https://docs.livekit.io/agents/models/tts/
tts=inference.TTS( tts=inference.TTS(
@@ -115,7 +115,9 @@ async def my_agent(ctx: JobContext):
noise_cancellation.BVCTelephony() noise_cancellation.BVCTelephony()
if params.participant.kind if params.participant.kind
== rtc.ParticipantKind.PARTICIPANT_KIND_SIP == rtc.ParticipantKind.PARTICIPANT_KIND_SIP
else noise_cancellation.BVC() else ai_coustics.audio_enhancement(
model=ai_coustics.EnhancerModel.QUAIL_VF_L
)
), ),
), ),
), ),