feat(eot): add audio models AGT-2520

AGENTS.md

@@ -35,6 +35,7 @@ it.
 | Marker | Flag | Meaning |
 |--------|------|---------|
 | `pytest.mark.unit` | `--unit` | fast, hermetic, no external providers/credentials/network |
+| `pytest.mark.audio_eot` | `--audio_eot` | hermetic audio end-of-turn / turn-detection suite |
 | `pytest.mark.plugin("name")` | `--plugin [name]` | provider integration test (needs that provider's deps/keys) |
 | `pytest.mark.stt` | `--stt` | cross-provider speech-to-text suite (`tests/test_stt.py`) |
 | `pytest.mark.tts` | `--tts` | cross-provider text-to-speech suite (`tests/test_tts.py`) |

MODEL_LICENSE

@@ -0,0 +1,113 @@
+LIVEKIT MODEL LICENSE AGREEMENT
+
+1. Introduction
+
+   LiveKit Incorporated ("LiveKit") is making available its proprietary models for
+   use pursuant to the terms and conditions of this Agreement. As further
+   described below, you may use these LiveKit models freely but can only use them
+   together with the LiveKit Agents framework. You cannot use the LiveKit models
+   on a standalone basis or with any other frameworks.
+
+   BY CLICKING "I ACCEPT," OR BY DOWNLOADING, INSTALLING, OR OTHERWISE ACCESSING
+   OR USING THE LIVEKIT MATERIALS, YOU AGREE THAT YOU HAVE READ AND UNDERSTOOD,
+   AND, AS A CONDITION TO YOUR USE OF THE LIVEKIT MATERIALS, YOU AGREE TO BE
+   BOUND BY, THE FOLLOWING TERMS AND CONDITIONS.
+
+2. Definitions
+
+   "Agreement" means this LiveKit Model License Agreement.
+
+   "Documentation" means the specifications, manuals, and documentation
+   accompanying any LiveKit Model and distributed by LiveKit.
+
+   "Licensee" or "you" means the individual or entity agreeing to be bound by
+   this Agreement.
+
+   "LiveKit Agents" means the proprietary LiveKit software framework for building
+   real-time multimodal AI applications with programmable backend participants.
+
+   "LiveKit Materials" means, collectively, the LiveKit Models and Documentation.
+
+   "LiveKit Model" means any of LiveKit's proprietary software models or
+   algorithms, including machine-learning software code, model weights,
+   inference-enabling software code, training-enabling software code, and
+   fine-tuning enabling software code. Any derivative works of a LiveKit Model,
+   whether developed by LiveKit, you, or any third party, will be deemed the
+   "LiveKit Model" for the purposes of this Agreement.
+
+3. License Rights
+
+   Right to Use LiveKit Materials. Subject to the terms and conditions of this
+   Agreement, including the requirements of Section 3.b, LiveKit grants you a
+   nonexclusive, nontransferable, worldwide, royalty-free license under LiveKit's
+   intellectual property rights to use, reproduce, distribute, copy, and create
+   derivative works of the LiveKit Materials.
+
+   Limitation on Use. As a condition to your use of the LiveKit Materials, you
+   agree: (i) not to use any LiveKit Models on a standalone basis or with any
+   frameworks other than LiveKit Agents; (ii) not to use any LiveKit Materials or
+   any output from, or results of using, LiveKit Models (including any derivative
+   works thereof) to improve or otherwise develop any other models that are not
+   LiveKit Models; or (iii) distribute or otherwise make available the LiveKit
+   Materials (including any derivative works thereof) except (x) pursuant to the
+   terms of this Agreement, and (y) you reproduce the above copyright notice.
+
+4. Intellectual Property
+
+   The LiveKit Materials are owned by LiveKit and its licensors. Except for the
+   rights granted to you under this Agreement, all rights are reserved and no
+   other express or implied rights are granted.
+
+   You will own any derivative works that you created from the LiveKit Materials,
+   subject to the terms of this Agreement.
+
+5. Disclaimer
+
+   UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING, LIVEKIT PROVIDES
+   THE LIVEKIT MATERIALS, AND ANY OUTPUT OR RESULTS THEREFROM, ON AN "AS IS"
+   BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED,
+   INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OR CONDITIONS OF TITLE,
+   NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU
+   ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR
+   REDISTRIBUTING THE LIVEKIT MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR
+   USE OF THE LIVEKIT MATERIALS AND ANY OUTPUT AND RESULTS.
+
+6. Limitation of Liability
+
+   IN NO EVENT AND UNDER NO LEGAL THEORY, WHETHER IN TORT (INCLUDING NEGLIGENCE),
+   CONTRACT, OR OTHERWISE, UNLESS REQUIRED BY APPLICABLE LAW (SUCH AS DELIBERATE
+   AND GROSSLY NEGLIGENT ACTS) OR AGREED TO IN WRITING, WILL LIVEKIT BE LIABLE TO
+   YOU FOR INDIRECT DAMAGES, INCLUDING ANY SPECIAL, INCIDENTAL, OR CONSEQUENTIAL
+   DAMAGES OF ANY CHARACTER ARISING AS A RESULT OF THIS AGREEMENT OR OUT OF THE
+   USE OR INABILITY TO USE THE LIVEKIT MATERIALS OR ANY OUTPUT OR RESULTS
+   THEREFROM (INCLUDING BUT NOT LIMITED TO DAMAGES FOR LOSS OF GOODWILL, WORK
+   STOPPAGE, COMPUTER FAILURE OR MALFUNCTION, OR ANY AND ALL OTHER COMMERCIAL
+   DAMAGES OR LOSSES), EVEN IF LIVEKIT HAS BEEN ADVISED OF THE POSSIBILITY OF
+   SUCH DAMAGES.
+
+7. Trademarks
+
+   This Agreement does not grant permission to use the trade names, trademarks,
+   service marks, or product names of LiveKit, except as required for reasonable
+   and customary use in describing the origin of the LiveKit Materials.
+
+8. Term and Termination
+
+   The term of this Agreement commences upon your acceptance of this Agreement
+   and continues in effect until you cease using the LiveKit Materials or it is
+   terminated by either party (on immediate written notice to the other party).
+   This Agreement will automatically terminate if you breach any of its terms.
+   Upon termination, you must immediately cease all use of the LiveKit Materials.
+   Sections 4, 5, 6, and 9 will survive termination.
+
+9. Governing Law and Venue
+
+   This Agreement is subject to the laws of the State of California, without
+   regard to its conflict of laws principles. The UN Convention on Contracts for
+   the International Sale of Goods does not apply to this Agreement. The courts
+   located in San Francisco, California, have exclusive jurisdiction for any
+   dispute arising out of this Agreement.
+
++ + + +
+
+Last Updated: November 25, 2024

README.md

@@ -47,7 +47,7 @@ agents that can see, hear, and understand.
 To install the core Agents library, along with plugins for popular model providers:
 
 ```bash
-pip install "livekit-agents[openai,silero,deepgram,cartesia,turn-detector]"
+pip install "livekit-agents[openai,deepgram,cartesia]"
 ```
 
 ## Docs and guides
@@ -92,7 +92,6 @@ from livekit.agents import (
     function_tool,
     inference,
 )
-from livekit.plugins import silero
 
 
 @function_tool
@@ -111,7 +110,7 @@ server = AgentServer()
 @server.rtc_session()
 async def entrypoint(ctx: JobContext):
     session = AgentSession(
-        vad=silero.VAD.load(),
+        vad=inference.VAD(),
         # any combination of STT, LLM, TTS, or realtime API can be used
         # this example shows LiveKit Inference, a unified API to access different models via LiveKit Cloud
         # to use model provider keys directly, replace with the following:
@@ -200,7 +199,7 @@ class StoryAgent(Agent):
 async def entrypoint(ctx: JobContext):
     userdata = StoryData()
     session = AgentSession[StoryData](
-        vad=silero.VAD.load(),
+        vad=inference.VAD(),
         stt="deepgram/nova-3",
         llm="openai/gpt-4.1-mini",
         tts="cartesia/sonic-3:9626c31c-bec5-4cca-baa8-f8ba9e84c8bc",
@@ -382,6 +381,10 @@ python myagent.py start
 
 Runs the agent with production-ready optimizations.
 
+## License
+
+The Agents framework is licensed under [Apache-2.0](LICENSE). The LiveKit turn detection models are licensed under the [LiveKit Model License](MODEL_LICENSE).
+
 ## Contributing
 
 The Agents framework is under active development in a rapidly evolving field. We welcome and appreciate contributions of any kind, be it feedback, bugfixes, features, new plugins and tools, or better documentation. You can file issues under this repo, open a PR, or chat with us in the [LiveKit community](https://docs.livekit.io/intro/community/).

examples/README.md

@@ -54,7 +54,7 @@ To run the examples, you'll need:
 
 - A [LiveKit Cloud](https://cloud.livekit.io) account or a local [LiveKit server](https://github.com/livekit/livekit)
 - API keys for the model providers you want to use in a `.env` file
-- Python 3.9 or higher
+- Python 3.10 or higher
 - [uv](https://docs.astral.sh/uv/)
 
 ### Environment file

examples/avatar_agents/audio_wave/agent_worker.py

@@ -18,7 +18,6 @@
 from livekit.agents.voice.avatar import DataStreamAudioOutput
 from livekit.agents.voice.io import PlaybackFinishedEvent, PlaybackStartedEvent
 from livekit.agents.voice.room_io import ATTRIBUTE_PUBLISH_ON_BEHALF
-from livekit.plugins import silero
 
 load_dotenv()
 
@@ -75,7 +74,6 @@ async def entrypoint(ctx: JobContext):
         stt=inference.STT("deepgram/nova-3"),
         llm=inference.LLM("google/gemini-2.5-flash"),
         tts=inference.TTS("cartesia/sonic-3"),
-        vad=silero.VAD.load(),
         resume_false_interruption=False,
     )
 

examples/avatar_agents/keyframe/agent_worker.py

@@ -14,9 +14,9 @@
     function_tool,
     inference,
 )
-from livekit.plugins import keyframe, silero
+from livekit.agents.inference import TurnDetector
+from livekit.plugins import keyframe
 from livekit.plugins.keyframe import Emotion
-from livekit.plugins.turn_detector.multilingual import MultilingualModel
 
 load_dotenv()
 
@@ -51,8 +51,7 @@ async def entrypoint(ctx: JobContext):
         llm=inference.LLM("google/gemini-2.5-flash"),
         tts=inference.TTS("cartesia/sonic-3"),
         resume_false_interruption=False,
-        vad=silero.VAD.load(),
-        turn_detection=MultilingualModel(),
+        turn_detection=TurnDetector(),
     )
 
     avatar = keyframe.AvatarSession(persona_slug="public:cosmo_persona-1.5-live")

examples/drive-thru/agent.py

@@ -34,8 +34,7 @@
     function_tool,
     inference,
 )
-from livekit.plugins import silero
-from livekit.plugins.turn_detector.multilingual import MultilingualModel
+from livekit.agents.inference import TurnDetector
 
 load_dotenv()
 
@@ -487,8 +486,7 @@ async def drive_thru_agent(ctx: JobContext) -> None:
         ),
         llm=inference.LLM("openai/gpt-4.1-mini"),
         tts=inference.TTS("cartesia/sonic-3", voice="f786b574-daa5-4673-aa0c-cbe3e8534c02"),
-        turn_detection=MultilingualModel(),
-        vad=silero.VAD.load(),
+        turn_detection=TurnDetector(),
         max_tool_steps=10,
     )
 

examples/frontdesk/agent.py

@@ -38,8 +38,7 @@
     task_completion_judge,
     tool_use_judge,
 )
-from livekit.plugins import silero
-from livekit.plugins.turn_detector.multilingual import MultilingualModel
+from livekit.agents.inference import TurnDetector
 
 load_dotenv()
 
@@ -266,8 +265,7 @@ async def frontdesk_agent(ctx: JobContext):
         stt=inference.STT("deepgram/nova-3"),
         llm=inference.LLM("google/gemini-2.5-flash"),
         tts=inference.TTS("cartesia/sonic-3", voice="39b376fc-488e-4d0c-8b37-e00b72059fdd"),
-        turn_detection=MultilingualModel(),
-        vad=silero.VAD.load(),
+        turn_detection=TurnDetector(),
         max_tool_steps=1,
     )
 

examples/healthcare/agent.py

@@ -32,7 +32,6 @@
     WarmTransferTask,
 )
 from livekit.agents.llm import ToolError, function_tool
-from livekit.plugins import silero
 
 logger = logging.getLogger("HealthcareAgent")
 
@@ -754,7 +753,6 @@ async def entrypoint(ctx: JobContext):
         stt=inference.STT("deepgram/nova-3", language="multi"),
         llm=inference.LLM("openai/gpt-4.1-mini"),
         tts=inference.TTS("inworld/inworld-tts-1"),
-        vad=silero.VAD.load(),
         preemptive_generation=True,
     )
 

examples/inference/agent.py

@@ -12,7 +12,6 @@
     cli,
     inference,
 )
-from livekit.plugins import silero
 from livekit.rtc import RpcInvocationData
 
 logger = logging.getLogger("inference")
@@ -59,7 +58,6 @@ async def entrypoint(ctx: JobContext) -> None:
         stt=inference.STT(model=DEFAULT_STT),
         llm=inference.LLM(model=DEFAULT_LLM),
         tts=inference.TTS(model=DEFAULT_TTS),
-        vad=silero.VAD.load(),
     )
 
     def parse_value(payload: str, fallback: str) -> str:

examples/other/elevenlab_scribe_v2.py

@@ -2,8 +2,8 @@
 
 from dotenv import load_dotenv
 
-from livekit.agents import Agent, AgentServer, AgentSession, JobContext, JobProcess, cli, inference
-from livekit.plugins import elevenlabs, silero
+from livekit.agents import Agent, AgentServer, AgentSession, JobContext, cli, inference
+from livekit.plugins import elevenlabs
 
 logger = logging.getLogger("realtime-scribe-v2")
 logger.setLevel(logging.INFO)
@@ -14,13 +14,6 @@
 server = AgentServer()
 
 
-def prewarm(proc: JobProcess) -> None:
-    proc.userdata["vad"] = silero.VAD.load()
-
-
-server.setup_fnc = prewarm
-
-
 @server.rtc_session()
 async def entrypoint(ctx: JobContext) -> None:
     # Using ElevenLabs STT plugin directly for realtime mode support
@@ -37,7 +30,6 @@ async def entrypoint(ctx: JobContext) -> None:
 
     session: AgentSession = AgentSession(
         allow_interruptions=True,
-        vad=ctx.proc.userdata["vad"],
         stt=stt,
         llm=inference.LLM("openai/gpt-4.1-mini"),
         tts=inference.TTS("cartesia/sonic-3"),

examples/other/kokoro_tts.py

@@ -2,9 +2,16 @@
 
 from dotenv import load_dotenv
 
-from livekit.agents import Agent, AgentServer, AgentSession, JobContext, JobProcess, cli, metrics
+from livekit.agents import (
+    Agent,
+    AgentServer,
+    AgentSession,
+    JobContext,
+    cli,
+    metrics,
+)
 from livekit.agents.voice import MetricsCollectedEvent
-from livekit.plugins import deepgram, openai, silero
+from livekit.plugins import deepgram, openai
 
 logger = logging.getLogger("kokoro-tts-agent")
 
@@ -27,13 +34,6 @@ def __init__(self) -> None:
 server = AgentServer()
 
 
-def prewarm(proc: JobProcess):
-    proc.userdata["vad"] = silero.VAD.load()
-
-
-server.setup_fnc = prewarm
-
-
 @server.rtc_session()
 async def entrypoint(ctx: JobContext):
     # each log entry will include these fields
@@ -42,7 +42,6 @@ async def entrypoint(ctx: JobContext):
         "user_id": "your user_id",
     }
     session = AgentSession(
-        vad=ctx.proc.userdata["vad"],
         # any combination of STT, LLM, TTS, or realtime API can be used
         llm=openai.LLM(model="gpt-4.1-mini"),
         stt=deepgram.STT(model="nova-3", language="multi"),

examples/other/transcription/multi-user-transcriber.py

@@ -10,15 +10,13 @@
     AgentSession,
     AutoSubscribe,
     JobContext,
-    JobProcess,
     StopResponse,
     cli,
     inference,
     llm,
     room_io,
     utils,
 )
-from livekit.plugins import silero
 
 load_dotenv()
 
@@ -91,9 +89,7 @@ async def _start_session(self, participant: rtc.RemoteParticipant) -> AgentSessi
         if participant.identity in self._sessions:
             return self._sessions[participant.identity]
 
-        session = AgentSession(
-            vad=self.ctx.proc.userdata["vad"],
-        )
+        session = AgentSession()
         await session.start(
             agent=Transcriber(
                 participant_identity=participant.identity,
@@ -136,11 +132,5 @@ async def cleanup():
     ctx.add_shutdown_callback(cleanup)
 
 
-def prewarm(proc: JobProcess):
-    proc.userdata["vad"] = silero.VAD.load()
-
-
-server.setup_fnc = prewarm
-
 if __name__ == "__main__":
     cli.run_app(server)