### Run a LiveKit Agent Example

Source: https://github.com/livekit/agents/blob/main/README.md

Executes a specific agent example from the 'examples' directory in development mode, requiring an '.env' file with credentials.

```shell
uv run examples/voice_agents/basic_agent.py dev
```

--------------------------------

### Install livekit-plugins-keyframe

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-keyframe/README.md

Install the Keyframe plugin using pip.

```bash
pip install livekit-plugins-keyframe
```

--------------------------------

### Install LiveKit Fish Audio Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-fishaudio/README.md

Install the `livekit-plugins-fishaudio` package using pip.

```bash
pip install livekit-plugins-fishaudio
```

--------------------------------

### Run Respeecher TTS Example

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-respeecher/README.md

Execute the provided example script to try out the Respeecher plugin.

```bash
uv run python examples/other/text-to-speech/respeecher_tts.py start
```

--------------------------------

### Install LiveKit Krisp Plugin and Krisp Audio SDK

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-krisp/README.md

Install the LiveKit Krisp plugin via pip. Note that the proprietary `krisp-audio` SDK must be obtained and installed separately from Krisp.

```bash
# Install the plugin
pip install livekit-plugins-krisp

# Install krisp-audio SDK separately (required for actual usage)
```

--------------------------------

### Install LiveKit Resemble Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-resemble/README.md

Install the LiveKit Resemble plugin using pip.

```bash
pip install livekit-plugins-resemble
```

--------------------------------

### Run Realtime Transcription Example

Source: https://github.com/livekit/agents/blob/main/examples/other/transcription/README.md

Set the necessary environment variables for LiveKit and OpenAI, then execute the Python script to start the realtime transcription agent.

```bash
export LIVEKIT_URL=wss://yourhost.livekit.cloud
export LIVEKIT_API_KEY=livekit-api-key
export LIVEKIT_API_SECRET=your-api-secret
export OPENAI_API_KEY=your-api-key

python3 transcriber.py start
```

--------------------------------

### Run LemonSlice Avatar Agent Locally

Source: https://github.com/livekit/agents/blob/main/examples/avatar/README.md

Install dependencies and start the agent locally. Ensure LiveKit and LemonSlice API keys are configured as environment variables before running.

```bash
pip install -r requirements.txt
python agent.py dev
```

--------------------------------

### Install LiveKit AsyncAI Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-asyncai/README.md

Install the LiveKit AsyncAI plugin using pip.

```bash
pip install livekit-plugins-asyncai
```

--------------------------------

### Install LiveKit NVIDIA Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-nvidia/README.md

Install the LiveKit NVIDIA plugin using pip.

```bash
pip install livekit-plugins-nvidia
```

--------------------------------

### Install ElevenLabs Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-elevenlabs/README.md

Use pip to install the ElevenLabs plugin for LiveKit Agents.

```bash
pip install livekit-plugins-elevenlabs
```

--------------------------------

### Install LiveKit Camb.ai Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-cambai/README.md

Install the LiveKit Camb.ai plugin using pip.

```bash
pip install livekit-plugins-cambai
```

--------------------------------

### Run the Phonic Realtime Agent Example

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-phonic/README.md

Navigate to the examples directory and run the Phonic realtime agent in development mode using `uv`.

```bash
cd examples
uv run voice_agents/phonic_realtime_agent.py dev
```

--------------------------------

### Install NLTK Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-nltk/README.md

Install the LiveKit NLTK plugin using pip.

```bash
pip install livekit-plugins-nltk
```

--------------------------------

### Install LiveKit Simplismart Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-simplismart/README.md

Use pip to install the Simplismart plugin for LiveKit Agents.

```bash
pip install livekit-plugins-simplismart
```

--------------------------------

### Install Project Dependencies

Source: https://github.com/livekit/agents/blob/main/AGENTS.md

Installs all project dependencies, including development extras, using the uv package manager.

```bash
make install          # Install all dependencies with dev extras (uv sync --all-extras --dev)
```

--------------------------------

### Install LiveKit Simli Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-simli/README.md

Run this command to install the LiveKit Simli plugin using pip.

```bash
pip install livekit-plugins-simli
```

--------------------------------

### Run a LiveKit Agent Example from Console

Source: https://github.com/livekit/agents/blob/main/examples/README.md

Execute this command to run a specific LiveKit agent example, such as basic_agent.py, directly in the console.

```bash
uv run examples/voice_agents/basic_agent.py console
```

--------------------------------

### Install LiveKit Groq Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-groq/README.md

Use this command to install the LiveKit Groq plugin and its dependencies via pip.

```bash
pip install livekit-plugins-groq
```

--------------------------------

### Install LiveKit Mistral AI Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-mistralai/README.md

Installs the core LiveKit plugin for Mistral AI services.

```bash
pip install livekit-plugins-mistralai
```

--------------------------------

### Install Anam Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-anam/README.md

Install the Anam plugin for LiveKit Agents using pip.

```bash
pip install livekit-plugins-anam
```

--------------------------------

### Install LiveKit AWS Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-aws/README.md

Install the core LiveKit AWS plugin or include the '[realtime]' extra for Nova Sonic models.

```bash
pip install livekit-plugins-aws

# For Nova Sonic realtime models
pip install livekit-plugins-aws[realtime]
```

--------------------------------

### Start LiveKit Avatar Dispatcher Server (Bash)

Source: https://github.com/livekit/agents/blob/main/examples/avatar_agents/audio_wave/README.md

Use this command to start the avatar dispatcher server. Optionally specify a port for the server to listen on.

```bash
python examples/avatar/dispatcher.py [--port 8089]
```

--------------------------------

### Install LiveKit Soniox Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-soniox/README.md

Install the Soniox plugin for LiveKit Agents using pip.

```bash
pip install livekit-plugins-soniox
```

--------------------------------

### Install livekit-plugins-fal

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-fal/README.md

Use pip to install the fal plugin for LiveKit Agents, enabling fal.ai integration.

```bash
pip install livekit-plugins-fal
```

--------------------------------

### Install LiveKit Baseten Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-baseten/README.md

Install the LiveKit Baseten plugin using pip to enable Baseten model integrations.

```bash
pip install livekit-plugins-baseten
```

--------------------------------

### Install LiveKit Gladia Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-gladia/README.md

Use pip to install the LiveKit Gladia plugin, which provides speech-to-text capabilities for LiveKit Agents.

```bash
pip install livekit-plugins-gladia
```

--------------------------------

### Install LiveKit Protoface Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-protoface/README.md

Use pip to install the livekit-plugins-protoface package, enabling Protoface virtual avatar support for LiveKit Agents.

```bash
pip install livekit-plugins-protoface
```

--------------------------------

### Install LiveAvatar Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-liveavatar/README.md

Use this command to install the LiveAvatar plugin for LiveKit Agents via pip.

```bash
pip install livekit-plugins-liveavatar
```

--------------------------------

### Download the realtime_joke_teller.py example script

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-aws/README.md

Downloads the `realtime_joke_teller.py` example script from the LiveKit agents GitHub repository to your local machine.

```bash
curl -O https://raw.githubusercontent.com/livekit/agents/main/examples/voice_agents/realtime_joke_teller.py
```

--------------------------------

### Install LiveKit AssemblyAI Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-assemblyai/README.md

Use this command to install the LiveKit AssemblyAI plugin via pip.

```bash
pip install livekit-plugins-assemblyai
```

--------------------------------

### Install LiveKit Silero Plugin for Realtime STT

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-mistralai/README.md

Installs the Silero plugin, a prerequisite for using Voxtral Realtime streaming STT.

```bash
pip install livekit-plugins-silero
```

--------------------------------

### Install LiveKit Smallest AI Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-smallestai/README.md

Use pip to install the LiveKit plugin for integrating Smallest AI functionalities into your project.

```bash
pip install livekit-plugins-smallestai
```

--------------------------------

### Install LiveKit MiniMax Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-minimax/README.md

Use this command to install the MiniMax TTS plugin for LiveKit Agents via pip.

```bash
pip install livekit-plugins-minimax-ai
```

--------------------------------

### Install livekit-plugins-runway

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-runway/README.md

Use pip to install the livekit-plugins-runway package, which provides the necessary components for Runway avatar integration.

```bash
pip install livekit-plugins-runway
```

--------------------------------

### Install LiveKit OpenAI Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-openai/README.md

Use this command to install the LiveKit OpenAI plugin and its dependencies via pip.

```bash
pip install livekit-plugins-openai
```

--------------------------------

### Start the Protoface Avatar Agent Worker

Source: https://github.com/livekit/agents/blob/main/examples/avatar_agents/protoface/README.md

Execute this command to start the LiveKit Protoface avatar agent worker in development mode.

```bash
python examples/avatar_agents/protoface/agent_worker.py dev
```

--------------------------------

### Install LiveKit Rime Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-rime/README.md

Use pip to install the LiveKit Rime plugin, enabling voice synthesis capabilities for LiveKit Agents.

```bash
pip install livekit-plugins-rime
```

--------------------------------

### Start LiveKit Agent Worker (Bash)

Source: https://github.com/livekit/agents/blob/main/examples/avatar_agents/audio_wave/README.md

Execute this command to start the agent worker. Provide the URL for the avatar dispatcher's launch endpoint.

```bash
python examples/avatar/agent_worker.py dev [--avatar-url http://localhost:8089/launch]
```

--------------------------------

### Install LiveKit Azure Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-azure/README.md

Use pip to install the `livekit-plugins-azure` package, which provides support for Azure AI services like Azure Speech.

```bash
pip install livekit-plugins-azure
```

--------------------------------

### Install Python dependencies for LiveKit AWS plugins

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-aws/README.md

Installs required Python packages including LiveKit AWS plugins, jokeapi, duckduckgo-search, python-weather, and python-dotenv for the example.

```bash
pip install livekit-plugins-aws[realtime] \
               jokeapi \
               duckduckgo-search \
               python-weather \
               python-dotenv
```

--------------------------------

### Run Text-to-Speech Example with uv

Source: https://github.com/livekit/agents/blob/main/examples/other/text-to-speech/README.md

Execute a specific text-to-speech plugin example to connect to a LiveKit room and stream TTS audio. Replace `{your_plugin}` with the desired plugin name.

```bash
uv run examples/other/text-to-speech/{your_plugin}_tts.py start
```

--------------------------------

### Start Mock Bank IVR System

Source: https://github.com/livekit/agents/blob/main/examples/telephony/bank-ivr/README.md

Run this command in a terminal to start the simulated banking IVR system, which will wait for incoming calls.

```bash
uv run python examples/bank-ivr/ivr_system_agent.py dev
```

--------------------------------

### Install LiveKit server on macOS

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-aws/README.md

Installs the LiveKit server using Homebrew on macOS, which is useful for local testing without LiveKit Cloud.

```bash
brew install livekit  # macOS
```

--------------------------------

### Install LiveKit Hamming Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-hamming/README.md

Install the LiveKit Hamming plugin from a local repository or extracted source archive using pip.

```bash
python -m pip install ./livekit-plugins/livekit-plugins-hamming
```

--------------------------------

### Install LiveKit Sarvam Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-sarvam/README.md

Install the LiveKit Sarvam plugin using pip to enable Sarvam.ai integrations for LiveKit Agents.

```bash
pip install livekit-plugins-sarvam
```

--------------------------------

### Create a Simple Voice Assistant with LiveKit Ultravox

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-ultravox/README.md

This example demonstrates how to initialize an AgentSession with RealtimeModel to create a basic voice assistant using Ultravox for speech-to-speech AI.

```python
import asyncio
from livekit.agents import Agent, AgentSession, JobContext, WorkerOptions, cli, inference
from livekit.plugins.ultravox.realtime import RealtimeModel

async def entrypoint(ctx: JobContext):
    await ctx.connect()
    
    session: AgentSession[None] = AgentSession(
        allow_interruptions=True,
        vad=inference.VAD(),
        llm=RealtimeModel(
            model_id="fixie-ai/ultravox",
            voice="Mark",
        ),
    )
    
    await session.start(
        agent=Agent(
            instructions="You are a helpful voice assistant.",
        ),
        room=ctx.room,
    )

if __name__ == "__main__":
    cli.run_app(WorkerOptions(entrypoint_fnc=entrypoint))
```

--------------------------------

### Complete LiveKit Voice Agent with Inworld STT and TTS

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-inworld/README.md

A comprehensive example demonstrating a LiveKit voice agent that integrates Inworld for both speech-to-text and text-to-speech, including agent setup and session management.

```python
import logging

from dotenv import load_dotenv

from livekit.agents import (
    Agent,
    AgentServer,
    AgentSession,
    JobContext,
    cli,
    inference,
    metrics,
    room_io,
)
from livekit.agents.inference import TurnDetector
from livekit.plugins import inworld

logger = logging.getLogger("inworld-agent")

load_dotenv()


class InworldAgent(Agent):
    def __init__(self) -> None:
        super().__init__(
            instructions=(
                "Your name is Nova. You interact with users via voice. "
                "Keep your responses concise and to the point. "
                "Do not use emojis, asterisks, markdown, or other special characters. "
                "You are helpful, curious, and friendly."
            ),
        )

    async def on_enter(self):
        self.session.generate_reply()


server = AgentServer()


@server.rtc_session()
async def entrypoint(ctx: JobContext):
    ctx.log_context_fields = {"room": ctx.room.name}

    session = AgentSession(
        stt=inworld.STT(model="inworld/inworld-stt-1"),
        llm="openai/gpt-4.1-mini",
        tts=inworld.TTS(voice="Clive"),
        turn_detection=TurnDetector(),
        vad=inference.VAD(),
    )

    usage_collector = metrics.UsageCollector()

    @session.on("metrics_collected")
    def _on_metrics(ev):
        metrics.log_metrics(ev.metrics)
        usage_collector.collect(ev.metrics)

    async def log_usage():
        logger.info(f"Usage: {usage_collector.get_summary()}")

    ctx.add_shutdown_callback(log_usage)

    await session.start(
        agent=InworldAgent(),
        room=ctx.room,
        room_options=room_io.RoomOptions(),
    )


if __name__ == "__main__":
    cli.run_app(server)
```

--------------------------------

### Install SLNG Plugin for LiveKit Agents

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-slng/README.md

Use pip to install the `livekit-plugins-slng` package, enabling SLNG integration with LiveKit Agents.

```bash
pip install livekit-plugins-slng
```

--------------------------------

### Install LiveKit Spitch Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-spitch/README.md

Use pip to install the LiveKit Spitch plugin, which provides African-language voice AI services for LiveKit Agents.

```bash
pip install livekit-plugins-spitch
```

--------------------------------

### Initialize and Run a LiveKit Agent Session in Python

Source: https://github.com/livekit/agents/blob/main/livekit-agents/README.md

This snippet demonstrates how to set up and run a LiveKit Agent, connecting to a room, configuring an OpenAI real-time model, and initiating a conversation with initial instructions.

```python
from dotenv import load_dotenv

from livekit import agents
from livekit.agents import AgentSession, Agent, RoomInputOptions
from livekit.plugins import openai

load_dotenv()

async def entrypoint(ctx: agents.JobContext):
    await ctx.connect()

    session = AgentSession(
        llm=openai.realtime.RealtimeModel(
            voice="coral"
        )
    )

    await session.start(
        room=ctx.room,
        agent=Agent(instructions="You are a helpful voice AI assistant.")
    )

    await session.generate_reply(
        instructions="Greet the user and offer your assistance."
    )


if __name__ == "__main__":
    agents.cli.run_app(agents.WorkerOptions(entrypoint_fnc=entrypoint))
```

--------------------------------

### Install LiveKit LemonSlice Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-lemonslice/README.md

Use pip to install the LiveKit LemonSlice plugin, enabling support for the LemonSlice virtual avatar.

```bash
pip install livekit-plugins-lemonslice
```

--------------------------------

### Initialize Fish Audio TTS with LiveKit Agent

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-fishaudio/README.md

Demonstrates basic initialization of the Fish Audio TTS plugin within a LiveKit Agent session, using credentials from environment variables.

```python
from livekit.agents import AgentSession
from livekit.plugins import fishaudio

# Basic usage with env-based credentials
tts = fishaudio.TTS()

session = AgentSession(
    tts=tts,
    # ... stt, llm, etc.
)
```

--------------------------------

### Install LiveKit Ultravox Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-ultravox/README.md

Use pip to install the LiveKit Ultravox plugin, enabling its features within your LiveKit Agents project.

```bash
pip install livekit-plugins-ultravox
```

--------------------------------

### Install LiveKit Uplift AI Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-upliftai/README.md

Use pip to install the `livekit-plugins-upliftai` package, adding Uplift AI voice synthesis capabilities to LiveKit Agents.

```bash
pip install livekit-plugins-upliftai
```

--------------------------------

### Install LiveKit xAI Plugin with pip

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-xai/README.md

Use pip to install the LiveKit xAI plugin, enabling integration with xAI's Grok services.

```bash
pip install livekit-plugins-xai
```

--------------------------------

### Using instructions for System-Level Commands

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-aws/README.md

This example demonstrates using the `instructions` parameter with `generate_reply()` to send system-level commands to the model, triggering immediate generation without appearing in conversation history.

```python
await session.generate_reply(
    instructions="Greet the user warmly and ask how you can help"
)
```

--------------------------------

### Install LiveKit Browser Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-browser/README.md

Use this command to install the LiveKit Browser plugin via pip. CEF binaries are downloaded automatically on first use.

```bash
pip install livekit-plugins-browser
```

--------------------------------

### Recommended Resemble TTS Usage with Async Context Manager

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-resemble/README.md

This example demonstrates the recommended way to use the Resemble TTS plugin with an async context manager for automatic resource cleanup, including one-off and real-time streaming synthesis.

```python
import asyncio
from livekit.plugins.resemble import TTS

async def run_tts_example():
    # Use TTS with async context manager for automatic resource cleanup
    async with TTS(
        api_key="your_api_key",  # or set RESEMBLE_API_KEY environment variable
        voice_uuid="your_voice_uuid",
        # Optional parameters
        sample_rate=44100,  # Sample rate in Hz (default: 44100)
        precision="PCM_16",  # Audio precision (PCM_32, PCM_24, PCM_16, MULAW)
        output_format="wav"  # Output format (wav or mp3)
    ) as tts:
        # One-off synthesis (uses REST API)
        audio_stream = tts.synthesize("Hello, world!")
        
        # Process chunks as they arrive
        async for chunk in audio_stream:
            # Audio data is in the 'frame.data' attribute of SynthesizedAudio objects
            audio_data = chunk.frame.data
            print(f"Received chunk: {len(audio_data)} bytes")
        
        # Alternative: collect all audio at once into a single AudioFrame
        audio_stream = tts.synthesize("Another example sentence.")
        audio_frame = await audio_stream.collect()
        print(f"Collected complete audio: {len(audio_frame.data)} bytes")
        
        # Real-time streaming synthesis (uses WebSocket API)
        # Only available for Business plan users in Resemble AI
        stream = tts.stream()
        await stream.synthesize_text("Hello, world!")
        


# Run the example
asyncio.run(run_tts_example())
```

--------------------------------

### Initialize Gladia STT with Basic Options

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-gladia/README.md

Initialize the Gladia STT client with an API key and enable interim results. The API key can also be provided via the GLADIA_API_KEY environment variable.

```python
from livekit.stt import STT
from livekit.plugins.gladia.stt import STT as GladiaSTT

# Basic initialization
stt = GladiaSTT(
    api_key="your-api-key-here",  # or use GLADIA_API_KEY env var
    interim_results=True
)
```

--------------------------------

### Install LiveKit Respeecher Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-respeecher/README.md

Use pip to install the Respeecher plugin for LiveKit Agents.

```bash
pip install livekit-plugins-respeecher
```

--------------------------------

### Install LiveKit Neuphonic Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-neuphonic/README.md

Use pip to install the Neuphonic plugin for LiveKit Agents.

```bash
pip install livekit-plugins-neuphonic
```

--------------------------------

### Install D-ID LiveKit Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-did/README.md

Install the D-ID plugin for LiveKit Agents using pip.

```bash
pip install livekit-plugins-did
```

--------------------------------

### Install LiveKit Deepgram Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-deepgram/README.md

Use pip to install the Deepgram plugin for LiveKit Agents.

```bash
pip install livekit-plugins-deepgram
```

--------------------------------

### Install LiveKit Speechmatics Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-speechmatics/README.md

Install the Speechmatics STT plugin for LiveKit Agents using pip.

```bash
pip install livekit-plugins-speechmatics
```

--------------------------------

### Configure Environment Variables for Beyond Presence and LiveKit

Source: https://github.com/livekit/agents/blob/main/examples/avatar_agents/bey/README.md

Set up necessary API keys and LiveKit URL for Beyond Presence, OpenAI, and LiveKit services.

```bash
# Beyond Presence Config
export BEY_API_KEY="..."

# OpenAI config (or other models, tts, stt)
export OPENAI_API_KEY="..."

# LiveKit config
export LIVEKIT_API_KEY="..."
export LIVEKIT_API_SECRET="..."
export LIVEKIT_URL="..."
```

--------------------------------

### Install LiveKit Speechify Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-speechify/README.md

Install the Speechify TTS plugin for LiveKit Agents using pip.

```bash
pip install livekit-plugins-speechify
```

--------------------------------

### LiveKit Agent Full Voice Pipeline with Baseten

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-baseten/README.md

This example demonstrates a complete voice AI assistant pipeline, integrating Baseten for STT and TTS, and OpenAI for LLM within a LiveKit Agent session.

```python
import os
from livekit import agents
from livekit.agents import AgentSession, Agent, RoomInputOptions, inference
from livekit.plugins import baseten, openai, noise_cancellation
from livekit.agents.inference import TurnDetector

BASETEN_API_KEY = os.getenv("BASETEN_API_KEY")
whisper_model_id = "your-whisper-model-id"  # or use chain_id for chain deployments
orpheus_model_id = "your-orpheus-model-id"


class Assistant(Agent):
    def __init__(self) -> None:
        super().__init__(instructions="You are a helpful voice AI assistant.")


async def entrypoint(ctx: agents.JobContext):
    session = AgentSession(
        stt=baseten.STT(
            api_key=BASETEN_API_KEY,
            model_id=whisper_model_id,  # or chain_id="your-chain-id"
            language="en",
            enable_partial_transcripts=True,
        ),
        llm=openai.LLM(
            api_key=BASETEN_API_KEY,
            base_url="https://inference.baseten.co/v1",
            model="openai/gpt-oss-120b",
        ),
        tts=baseten.TTS(
            api_key=BASETEN_API_KEY,
            model_endpoint=(
                f"https://model-{orpheus_model_id}"
                ".api.baseten.co/environments/production/predict"
            ),
        ),
        vad=inference.VAD(),
        turn_detection=TurnDetector(),
    )

    await session.start(
        room=ctx.room,
        agent=Assistant(),
        room_input_options=RoomInputOptions(
            noise_cancellation=noise_cancellation.BVC(),
        ),
    )

    await session.generate_reply(
        instructions="Greet the user and offer your assistance."
    )


if __name__ == "__main__":
    agents.cli.run_app(agents.WorkerOptions(entrypoint_fnc=entrypoint))

```

--------------------------------

### Configure Environment and Start Agent for Third-Party Meetings

Source: https://github.com/livekit/agents/blob/main/examples/avatar_agents/lemonslice/README.md

Set environment variables for the meeting URL and chat listening preference, then start the agent worker specifically designed for third-party meeting integration.

```bash
export MEETING_URL="https://zoom.us/j/123456789?pwd=abcdef"
export LISTEN_TO_MEETING_CHAT="false"
python examples/avatar_agents/lemonslice/agent_worker_meeting.py dev
```

--------------------------------

### Install LiveKit BitHuman Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-bithuman/README.md

Use this command to install the LiveKit BitHuman plugin into your Python environment.

```bash
pip install livekit-plugins-bithuman
```

--------------------------------

### Install LiveKit AvatarTalk Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-avatartalk/README.md

Use this command to install the LiveKit AvatarTalk plugin via pip.

```bash
pip install livekit-plugins-avatartalk
```

--------------------------------

### Install Avatario Plugin with pip

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-avatario/README.md

Use this command to install the LiveKit Avatario plugin via pip.

```bash
pip install livekit-plugins-avatario
```

--------------------------------

### Generate Local Documentation with pdoc

Source: https://github.com/livekit/agents/blob/main/README.md

Use these shell commands to synchronize dependencies and build the LiveKit Agents SDK documentation locally into the 'docs' directory.

```shell
uv sync --all-extras --group docs
uv run --active pdoc --skip-errors --html --output-dir=docs livekit
```

--------------------------------

### Set up LiveKit API Keys in .env

Source: https://github.com/livekit/agents/blob/main/examples/README.md

This snippet shows the basic environment variables required in a .env file for connecting to a LiveKit server, including the URL, API key, and API secret.

```bash
LIVEKIT_URL="wss://your-project.livekit.cloud"
LIVEKIT_API_KEY="your_api_key"
LIVEKIT_API_SECRET="your_api_secret"
```

--------------------------------

### Start the AvatarTalk Agent Worker

Source: https://github.com/livekit/agents/blob/main/examples/avatar_agents/avatartalk/README.md

Execute this command to start the AvatarTalk agent worker in development mode.

```bash
python examples/avatar_agents/avatartalk/agent_worker.py dev
```

--------------------------------

### Install LiveKit Inworld Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-inworld/README.md

Use this command to install the Inworld plugin for LiveKit Agents via pip.

```bash
pip install livekit-plugins-inworld
```

--------------------------------

### Install LiveKit Agent Dependencies with uv

Source: https://github.com/livekit/agents/blob/main/examples/README.md

Run this command from the repository root to install all necessary project dependencies, including development extras, using the uv package manager.

```bash
uv sync --all-extras --dev
```

--------------------------------

### Install LiveKit TruGen Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-trugen/README.md

Use this command to install the LiveKit TruGen AI plugin using pip.

```bash
pip install livekit-plugins-trugen
```

--------------------------------

### Install LiveKit Tavus Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-tavus/README.md

Use this command to install the Tavus plugin for LiveKit Agents via pip.

```bash
pip install livekit-plugins-tavus
```

--------------------------------

### Initialize Gladia STT with Advanced Configuration

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-gladia/README.md

Configure the Gladia STT client with various advanced options including multi-language support, audio parameters, translation settings, custom vocabulary, and custom spelling.

```python
stt = GladiaSTT(
    languages=["en", "fr"],                     # Specify languages or let Gladia auto-detect
    code_switching=True,                        # Allow switching between languages during recognition
    sample_rate=16000,                          # Audio sample rate in Hz
    bit_depth=16,                               # Audio bit depth
    channels=1,                                 # Number of audio channels
    region="eu-west",                            # Specify Region to use for the Gladia API
    encoding="wav/pcm",                         # Audio encoding format
    energy_filter=True,                         # Enable voice activity detection
    translation_enabled=True,
    translation_target_languages=["en"],
    translation_model="base",
    translation_match_original_utterances=True,
    translation_context_adaptation= False,      # Enable context-aware translation
    translation_context= None,                  # Context input to guide translation
    translation_informal=False,                 # Use informal tone in translation
    pre_processing_audio_enhancer=False,        # Apply pre-processing to the audio stream to enhance the quality
    pre_processing_speech_threshold=0.6,        # Sensitivity for speech detection; closer to 1 = stricter, less background noise

    # Custom_vocabulary exemple
    custom_vocabulary=[
        "Westeros",
        {"value": "Stark"},
        {
            "value": "Night's Watch",
            "pronunciations": ["Nightz Watch"],
            "intensity": 0.4,
            "language": "en"
        }
    ],

    # Custom_spelling exemple
    custom_spelling={
        "Gorish": ["ghorish", "gaurish", "gaureish"],
        "Data Science": ["data-science", "data science"],
        ".": ["period", "full stop"],
        "SQL": ["sequel"]
    }
)
```

--------------------------------

### Install LiveKit Agents with Model Provider Plugins

Source: https://github.com/livekit/agents/blob/main/README.md

Use this command to install the core LiveKit Agents library along with specified plugins for popular model providers like OpenAI, Deepgram, and Cartesia.

```bash
pip install "livekit-agents[openai,deepgram,cartesia]"
```

--------------------------------

### Configure and Attach Hamming Session in Python

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-hamming/README.md

This example demonstrates how to configure the Hamming plugin with API keys and an external agent ID, then attach it to an AgentSession with customer metadata, external links, and a session mode.

```python
import os

from livekit.agents import AgentSession, JobContext
from livekit.plugins import hamming


async def entrypoint(ctx: JobContext) -> None:
    await ctx.connect()

    hamming.configure_hamming(
        api_key=os.environ["HAMMING_API_KEY"],
        external_agent_id=os.environ["HAMMING_EXTERNAL_AGENT_ID"],
        recording={"mode": "session_audio"},
    )

    session = AgentSession()
    hamming.attach_session(
        session,
        job_ctx=ctx,
        customer_metadata={
            "deployment": {
                "environment": "prod",
                "prompt_version": "v17",
            },
            "experiment": {
                "variant": "B",
            },
        },
        external_links=[
            {
                "label": "CRM Contact",
                "url": "https://crm.example.com/contact/123",
                "source": "salesforce",
            }
        ],
        session_mode="testing",
    )
```

--------------------------------

### Configure Environment Variables for Protoface, Google, and LiveKit

Source: https://github.com/livekit/agents/blob/main/examples/avatar_agents/protoface/README.md

Set the necessary environment variables for Protoface API key and avatar ID, Google API key, and LiveKit API credentials and URL before running the agent.

```bash
# Protoface config. PROTOFACE_AVATAR_ID is optional and defaults to av_stock_001.
export PROTOFACE_API_KEY="..."
export PROTOFACE_AVATAR_ID="av_stock_001"

# Google config
export GOOGLE_API_KEY="..."

# LiveKit config
export LIVEKIT_API_KEY="..."
export LIVEKIT_API_SECRET="..."
export LIVEKIT_URL="..."
```

--------------------------------

### Install livekit-plugins-gnani

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-gnani/README.md

Install the LiveKit Gnani plugin using pip, which also includes `websockets` and `livekit-agents` as dependencies.

```bash
pip install livekit-plugins-gnani
```

--------------------------------

### Install Clova Plugin for LiveKit Agents

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-clova/README.md

Use pip to install the Clova STT plugin for LiveKit Agents.

```bash
pip install livekit-plugins-clova
```

--------------------------------

### Install LiveKit Cerebras Plugin

Source: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-cerebras/README.md

Run this command to install the Cerebras plugin for LiveKit Agents using pip.

```bash
pip install livekit-plugins-cerebras
```

--------------------------------

### Start the LiveAvatar Agent Worker

Source: https://github.com/livekit/agents/blob/main/examples/avatar_agents/liveavatar/README.md

Execute this command to start the LiveKit LiveAvatar agent worker in development mode.

```bash
python examples/avatar_agents/liveavatar/agent_worker.py dev
```