### Setup and Run Node.js LiveKit Agents Example

Source: https://docs.cartesia.ai/integrations/live-kit

Clone the livekit/agents-js repository, install dependencies, build the project, and run the Cartesia example agent. Requires CARTESIA_API_KEY, LIVEKIT credentials, and an LLM provider API key. Connect via WebRTC transport.

```bash
# clone and setup livekit/agents-js
git clone git@github.com:livekit/agents-js.git
cd agents-js
pnpm i && pnpm run build

# run with required API keys:
# - CARTESIA_API_KEY
# - LIVEKIT_URL, LIVEKIT_API_KEY, LIVEKIT_API_SECRET
# -  some LLM provider's API key
node ./examples/src/cartesia.ts dev

# go to https://agents-playground.livekit.io/
# find your agent (make sure you're in the right org)
# then connect to it with WebRTC transport
```

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

### Setup and Run Python LiveKit Agents Example

Source: https://docs.cartesia.ai/integrations/live-kit

Clone the livekit/agents repository, install dependencies, and run the Cartesia example agent. Requires CARTESIA_API_KEY, LIVEKIT credentials, and an LLM provider API key.

```bash
# clone and setup livekit/agents
git clone git@github.com:livekit/agents.git
cd agents
uv sync

# run with required API keys:
# - CARTESIA_API_KEY
# - LIVEKIT_URL, LIVEKIT_API_KEY, LIVEKIT_API_SECRET
# -  some LLM provider's API key
uv run examples/other/cartesia.py console
```

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

### Install Exa-py for Examples

Source: https://docs.cartesia.ai/line/developer-tools/release-notes

Install exa-py for Exa web search integration in examples.

```bash
exa-py
```

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

### Run Get Voice Example (Python)

Source: https://docs.cartesia.ai/llms-full.txt

Instructions to clone the repository, install dependencies, and run the Python example for getting a voice. Requires setting the CARTESIA_API_KEY.

```sh
git clone --branch v3.2.0 https://github.com/cartesia-ai/cartesia-python
cd cartesia-python
uv sync
CARTESIA_API_KEY=YOUR_KEY uv run examples/examples.py voices_get [voice_id]
```

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

### Run Python Example

Source: https://docs.cartesia.ai/examples/voices-list

Clone the repository, install dependencies, and run the Python example to list voices. Ensure you set your CARTESIA_API_KEY environment variable.

```sh
git clone --branch v3.2.0 https://github.com/cartesia-ai/cartesia-python
cd cartesia-python
uv sync
CARTESIA_API_KEY=YOUR_KEY uv run examples/examples.py voices_list
```

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

### Run Get Voice Example (TypeScript)

Source: https://docs.cartesia.ai/llms-full.txt

Instructions to clone the repository, install dependencies, and run the TypeScript example for getting a voice. Requires setting the CARTESIA_API_KEY.

```sh
git clone --branch v3.2.0 https://github.com/cartesia-ai/cartesia-js
cd cartesia-js
pnpm i
CARTESIA_API_KEY=YOUR_KEY pnpm tsn examples/node_examples.ts voicesGet [voice_id]
```

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

### Install Duckduckgo-search for Examples

Source: https://docs.cartesia.ai/line/developer-tools/release-notes

Install duckduckgo-search for fallback web search functionality in examples.

```bash
duckduckgo-search
```

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

### Run TypeScript Example

Source: https://docs.cartesia.ai/examples/voices-list

Clone the repository, install dependencies, and run the TypeScript example to list voices. Ensure you set your CARTESIA_API_KEY environment variable.

```sh
git clone --branch v3.2.0 https://github.com/cartesia-ai/cartesia-js
cd cartesia-js
pnpm i
CARTESIA_API_KEY=YOUR_KEY pnpm tsn examples/node_examples.ts voicesList
```

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

### Run Python Error Handling Example

Source: https://docs.cartesia.ai/examples/error-handling

Instructions to clone the repository, install dependencies, and run the Python error handling example with an API key.

```sh
git clone --branch v3.2.0 https://github.com/cartesia-ai/cartesia-python
cd cartesia-python
uv sync
CARTESIA_API_KEY=YOUR_KEY uv run examples/examples.py error_handling_example
```

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

### Run TypeScript Error Handling Example

Source: https://docs.cartesia.ai/examples/error-handling

Instructions to clone the repository, install dependencies, and run the TypeScript error handling example with an API key.

```sh
git clone --branch v3.2.0 https://github.com/cartesia-ai/cartesia-js
cd cartesia-js
pnpm i
CARTESIA_API_KEY=YOUR_KEY pnpm tsn examples/node_examples.ts errorHandling
```

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

### Run Infill Audio Example (Async Python)

Source: https://docs.cartesia.ai/examples/infill-create

Command to execute the asynchronous infill audio creation example. This requires cloning the repository, installing dependencies, and setting your Cartesia API key.

```sh
git clone --branch v3.2.0 https://github.com/cartesia-ai/cartesia-python
cd cartesia-python
uv sync
CARTESIA_API_KEY=YOUR_KEY uv run examples/async_examples.py infill_create_async left.wav right.wav "transcript to infill"
```

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

### Run STT Transcribe Example (Python)

Source: https://docs.cartesia.ai/examples/stt-transcribe

Clone the Cartesia Python repository, install dependencies, and run the synchronous STT transcribe example. Ensure you set your CARTESIA_API_KEY.

```sh
git clone --branch v3.2.0 https://github.com/cartesia-ai/cartesia-python
cd cartesia-python
uv sync
CARTESIA_API_KEY=YOUR_KEY uv run examples/examples.py stt_transcribe
```

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

### Clone and Run Next.js Example

Source: https://docs.cartesia.ai/examples/nextjs

Clone the Cartesia.js repository, install dependencies, and run the Next.js example project locally. Ensure you replace 'YOUR_KEY' with your actual Cartesia API key.

```sh
git clone --branch v3.2.0 https://github.com/cartesia-ai/cartesia-js
cd cartesia-js/examples/nextjs
npm install
CARTESIA_API_KEY=YOUR_KEY npm run dev
```

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

### Run STT Transcribe Example (Python Async)

Source: https://docs.cartesia.ai/examples/stt-transcribe

Clone the Cartesia Python repository, install dependencies, and run the asynchronous STT transcribe example. Ensure you set your CARTESIA_API_KEY.

```sh
git clone --branch v3.2.0 https://github.com/cartesia-ai/cartesia-python
cd cartesia-python
uv sync
CARTESIA_API_KEY=YOUR_KEY uv run examples/async_examples.py stt_transcribe_async
```

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

### Run Python TTS WebSocket Basic Example

Source: https://docs.cartesia.ai/examples/tts-websocket-basic

Clone the repository, install dependencies, and run the basic TTS WebSocket example using Python. Ensure you set your CARTESIA_API_KEY.

```sh
git clone --branch v3.2.0 https://github.com/cartesia-ai/cartesia-python
cd cartesia-python
uv sync
CARTESIA_API_KEY=YOUR_KEY uv run examples/examples.py tts_websocket_basic
```

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

### Run STT Transcribe Example (TypeScript Node.js)

Source: https://docs.cartesia.ai/examples/stt-transcribe

Clone the Cartesia JavaScript repository, install dependencies, and run the Node.js STT transcribe example. Ensure you set your CARTESIA_API_KEY.

```sh
git clone --branch v3.2.0 https://github.com/cartesia-ai/cartesia-js
cd cartesia-js
pnpm i
CARTESIA_API_KEY=YOUR_KEY pnpm tsn examples/node_examples.ts sttTranscribe
```

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

### Clone and Run Python Async TTS Example

Source: https://docs.cartesia.ai/llms-full.txt

Clone the Cartesia Python repository, install dependencies, and run an asynchronous text-to-speech generation example. Ensure you set your CARTESIA_API_KEY.

```sh
git clone --branch v3.2.0 https://github.com/cartesia-ai/cartesia-python
cd cartesia-python
uv sync
CARTESIA_API_KEY=YOUR_KEY uv run examples/async_examples.py tts_generate_async
```

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

### Run Python Async TTS WebSocket Basic Example

Source: https://docs.cartesia.ai/examples/tts-websocket-basic

Clone the repository, install dependencies, and run the basic asynchronous TTS WebSocket example using Python. Ensure you set your CARTESIA_API_KEY.

```sh
git clone --branch v3.2.0 https://github.com/cartesia-ai/cartesia-python
cd cartesia-python
uv sync
CARTESIA_API_KEY=YOUR_KEY uv run examples/async_examples.py tts_websocket_basic_async
```

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

### Run STT Manual Finalize WebSocket Example (Python)

Source: https://docs.cartesia.ai/examples/stt-manual-finalize-websocket

Clone the Cartesia Python repository, install dependencies, and run the STT manual finalize WebSocket example. Ensure you replace 'YOUR_KEY' with your actual Cartesia API key.

```sh
git clone --branch v3.2.0 https://github.com/cartesia-ai/cartesia-python
cd cartesia-python
uv sync
CARTESIA_API_KEY=YOUR_KEY uv run examples/examples.py stt_manual_finalize_websocket
```

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

### Run STT Manual Finalize WebSocket Example (Python Async)

Source: https://docs.cartesia.ai/examples/stt-manual-finalize-websocket

Clone the Cartesia Python repository, install dependencies, and run the asynchronous STT manual finalize WebSocket example. Replace 'YOUR_KEY' with your Cartesia API key.

```sh
git clone --branch v3.2.0 https://github.com/cartesia-ai/cartesia-python
cd cartesia-python
uv sync
CARTESIA_API_KEY=YOUR_KEY uv run examples/async_examples.py stt_manual_finalize_websocket_async
```

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

### Quick Start: Establish WebSocket Connection and Stream Audio

Source: https://docs.cartesia.ai/line/integrations/websocket-api

This JavaScript snippet demonstrates how to establish a WebSocket connection, send a 'start' event to initialize the stream, handle incoming audio from the agent, and send audio data from the user.

```javascript
const ws = new WebSocket(
  `wss://api.cartesia.ai/agents/stream/${agentId}`,
  {
    headers: {
      Authorization: `Bearer ${accessToken}`,
      "Cartesia-Version": "2025-04-16",
    },
  }
);

// Initialize the stream
ws.onopen = () => {
  ws.send(JSON.stringify({
    event: "start",
    config: { input_format: "pcm_44100" },
  }));
};

// Handle agent audio
ws.onmessage = (msg) => {
  const data = JSON.parse(msg.data);
  if (data.event === "media_output") {
    playAudio(atob(data.media.payload));
  }
};

// Send user audio
function sendAudio(audioData) {
  ws.send(JSON.stringify({
    event: "media_input",
    stream_id: streamId,
    media: { payload: btoa(audioData) },
  }));
}
```

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

### Run Python TTS WebSocket Example

Source: https://docs.cartesia.ai/examples/tts-websocket-response-handling

Clones the cartesia-python repository, installs dependencies, and runs the TTS WebSocket response handling example.

```sh
git clone --branch v3.2.0 https://github.com/cartesia-ai/cartesia-python
cd cartesia-python
uv sync
CARTESIA_API_KEY=YOUR_KEY uv run examples/examples.py tts_websocket_response_handling
```

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

### Run Infill Audio Example (Python)

Source: https://docs.cartesia.ai/examples/infill-create

Command to clone the repository, set up dependencies, and run the synchronous infill audio creation example. Ensure you replace 'YOUR_KEY' with your actual Cartesia API key.

```sh
git clone --branch v3.2.0 https://github.com/cartesia-ai/cartesia-python
cd cartesia-python
uv sync
CARTESIA_API_KEY=YOUR_KEY uv run examples/examples.py infill_create left.wav right.wav "transcript to infill"
```

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

### Create Project from Example

Source: https://docs.cartesia.ai/line/cli

Creates a new project by cloning an example agent from the Cartesia repository.

```zsh
cartesia create
```

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

### Main Application Logic

Source: https://docs.cartesia.ai/llms-full.txt

Orchestrates the application startup, including connecting to TTS and Twilio WebSockets, setting up ngrok, and starting a call.

```javascript
async function main() {
    try {
      log('Starting application');

      await connectToTTSWebSocket();
      log('TTS WebSocket connected successfully');

      await testTTSWebSocket();
      log('TTS WebSocket test passed successfully');

      const twilioWebsocketPort = await setupTwilioWebSocket();
      log(`Twilio WebSocket server set up on port ${twilioWebsocketPort}`);

      const twilioWebsocketUrl = await setupNgrokTunnel(twilioWebsocketPort);

      await startCall(twilioWebsocketUrl);
    } catch (error) {
      log(`Error in main function: ${error.message}`);
    }
  }

    // Run the script
    main();
```

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

### Run TypeScript TTS WebSocket Example

Source: https://docs.cartesia.ai/examples/tts-websocket-response-handling

Clones the cartesia-js repository, installs dependencies, and runs the TTS WebSocket response handling example using Node.js.

```sh
git clone --branch v3.2.0 https://github.com/cartesia-ai/cartesia-js
cd cartesia-js
pnpm i
CARTESIA_API_KEY=YOUR_KEY pnpm tsn examples/node_examples.ts ttsWebsocketResponseHandling
```

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

### Run TTS SSE with Timestamps Example in Python

Source: https://docs.cartesia.ai/examples/tts-sse-with-timestamps

Clone the Cartesia Python repository, install dependencies, and run the synchronous TTS SSE with timestamps example.

```sh
git clone --branch v3.2.0 https://github.com/cartesia-ai/cartesia-python
cd cartesia-python
uv sync
CARTESIA_API_KEY=YOUR_KEY uv run examples/examples.py tts_sse_with_timestamps
```

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

### Clone and Run Python TTS Example

Source: https://docs.cartesia.ai/llms-full.txt

Clone the Cartesia Python repository, install dependencies, and run a text-to-speech generation example to a file. Ensure you set your CARTESIA_API_KEY.

```sh
git clone --branch v3.2.0 https://github.com/cartesia-ai/cartesia-python
cd cartesia-python
uv sync
CARTESIA_API_KEY=YOUR_KEY uv run examples/examples.py tts_generate_to_file
```

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

### Configure LlmAgent with Custom System Prompt and Tools

Source: https://docs.cartesia.ai/line/sdk/agents

Set up a detailed system prompt to define the agent's behavior and include specific tools like 'end_call'. This example demonstrates how to integrate the agent with the VoiceAgentApp.

```python
import os
from line import CallRequest
from line.llm_agent import LlmAgent, LlmConfig, end_call
from line.voice_agent_app import AgentEnv, VoiceAgentApp

SYSTEM_PROMPT = """You are a friendly customer service agent.

Rules:
- Be polite and empathetic
- Confirm understanding before taking action
-  end_call to gracefully end conversations
"""

async def get_agent(env: AgentEnv, call_request: CallRequest):
    return LlmAgent(
        model="anthropic/claude-haiku-4-5-20251001",
        api_key=os.getenv("ANTHROPIC_API_KEY"),
        tools=[end_call],
        config=LlmConfig(
            system_prompt=SYSTEM_PROMPT,
            introduction="Hello! How can I help you today?",
        ),
    )

app = VoiceAgentApp(get_agent=get_agent)

if __name__ == "__main__":
    app.run()
```

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

### Create and Initialize Agent Project

Source: https://docs.cartesia.ai/line/start-building/quickstart

Initializes a new agent project named 'my-voice-agent' and adds the 'cartesia-line' dependency using uv.

```bash
uv init my-voice-agent && cd my-voice-agent
uv add cartesia-line
```

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

### Example: Using knowledge_base Tool

Source: https://docs.cartesia.ai/llms-full.txt

This example includes the `knowledge_base` tool, allowing the LLM to retrieve information from attached documents. The LLM will call this tool to answer questions based on the provided knowledge base.

```python
# Knowledge base: look up the agent's attached documents
tools=[knowledge_base]  # LLM calls this to answer from uploaded docs
```

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

### Run TTS SSE with Timestamps Example in TypeScript

Source: https://docs.cartesia.ai/examples/tts-sse-with-timestamps

Clone the Cartesia JavaScript repository, install dependencies, and run the TTS SSE with timestamps example using Node.js.

```sh
git clone --branch v3.2.0 https://github.com/cartesia-ai/cartesia-js
cd cartesia-js
pnpm i
CARTESIA_API_KEY=YOUR_KEY pnpm tsn examples/node_examples.ts ttsSSEWithTimestamps
```

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

### Initialize Node.js Project

Source: https://docs.cartesia.ai/integrations/twilio

Initializes a new Node.js project. Run this command in your project's root directory.

```bash
npm init -y
```

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

### Run TTS SSE with Timestamps Example in Python (Async)

Source: https://docs.cartesia.ai/examples/tts-sse-with-timestamps

Clone the Cartesia Python repository, install dependencies, and run the asynchronous TTS SSE with timestamps example.

```sh
git clone --branch v3.2.0 https://github.com/cartesia-ai/cartesia-python
cd cartesia-python
uv sync
CARTESIA_API_KEY=YOUR_KEY uv run examples/async_examples.py tts_sse_with_timestamps_async
```

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

### Word Timestamps Response Example

Source: https://docs.cartesia.ai/api-reference/tts/websocket

An example of a response containing word-level timing information. This format is used to provide start and end times for each word in the synthesized speech.

```json
{
  "type": "timestamps",
  "done": false,
  "status_code": 206,
  "context_id": "872ec12d-bc63-4e1e-a241-4f58c879d105",
  "word_timestamps": {
    "words": [
      "Hello",
      "world"
    ],
    "start": [
      0,
      0.5
    ],
    "end": [
      0.4,
      0.9
    ]
  }
}
```

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

### Install Line SDK

Source: https://docs.cartesia.ai/line/sdk/overview

Use the uv package manager to add the Line SDK to your project.

```bash
uv add cartesia-line
```

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

### Clone and Run TypeScript TTS Example

Source: https://docs.cartesia.ai/llms-full.txt

Clone the Cartesia JavaScript repository, install dependencies, and run a text-to-speech generation example using Node.js. Ensure you set your CARTESIA_API_KEY.

```sh
git clone --branch v3.2.0 https://github.com/cartesia-ai/cartesia-js
cd cartesia-js
pnpm i
CARTESIA_API_KEY=YOUR_KEY pnpm tsn examples/node_examples.ts ttsGenerateToFile
```

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

### Install Python SDK

Source: https://docs.cartesia.ai/tools/client-libraries

Install the official Python SDK from PyPI. Includes optional support for websockets.

```sh
pip install --pre cartesia

# for websocket support
pip install 'cartesia[websockets]'
```

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

### Configure Built-in Tools

Source: https://docs.cartesia.ai/line/developer-tools/release-notes

Initialize an LlmAgent with standard tools like web search, DTMF sending, and call transfers.

```python
from line.llm_agent import end_call, send_dtmf, transfer_call, web_search, agent_as_handoff

agent = LlmAgent(
    tools=[
        end_call,                    # End the call
        send_dtmf,                   # Send DTMF tones
        transfer_call,               # Transfer to phone number
        web_search,                  # Real-time web search
        agent_as_handoff(other_agent, name="transfer_to_billing"),
    ],
    ...
)
```

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

### Run TypeScript TTS WebSocket Basic Example

Source: https://docs.cartesia.ai/examples/tts-websocket-basic

Clone the repository, install dependencies, and run the basic TTS WebSocket example using TypeScript. Ensure you set your CARTESIA_API_KEY.

```sh
git clone --branch v3.2.0 https://github.com/cartesia-ai/cartesia-js
cd cartesia-js
pnpm i
CARTESIA_API_KEY=YOUR_KEY pnpm tsn examples/node_examples.ts ttsWebsocketBasic
```

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

### Instantiate Router Agent with LlmAgents

Source: https://docs.cartesia.ai/llms-full.txt

Example of how to configure and use the RouterAgent with multiple specialized LlmAgents, including setting up their models and system prompts.

```python
async def get_agent(env, call_request):
    return RouterAgent(
        default_agent=LlmAgent(
            model="gpt-5-nano",
            api_key=os.getenv("OPENAI_API_KEY"),
            config=LlmConfig(system_prompt="You are a helpful assistant..."),
        ),
        specialists={
            "billing": LlmAgent(
                model="gpt-5-nano",
                api_key=os.getenv("OPENAI_API_KEY"),
                config=LlmConfig(system_prompt="You are a billing specialist..."),
            ),
            "technical": LlmAgent(
                model="anthropic/claude-haiku-4-5-20251001",
                api_key=os.getenv("ANTHROPIC_API_KEY"),
                config=LlmConfig(system_prompt="You are a technical support specialist..."),
            ),
        }
    )
```

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

### Create a New Agent

Source: https://docs.cartesia.ai/line/cli

Creates a new agent project from an example in the Line repository. Navigate into the created directory afterwards.

```zsh
cartesia create my-agent
# Choose any example you like.
cd my-agent
```

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

### List Templates

Source: https://docs.cartesia.ai/api-reference/agents/agents/templates

Lists public, Cartesia-provided agent templates to help you get started.

```APIDOC
## GET /agents/templates

### Description
List of public, Cartesia-provided agent templates to help you get started.

### Method
GET

### Endpoint
/agents/templates

### Parameters
#### Header Parameters
- **Cartesia-Version** (string) - Required - API version header. Example: '2026-03-01'

### Request Example
(No request body for GET request)

### Response
#### Success Response (200)
- **templates** (array) - List of agent templates.
  - **id** (string) - The ID of the agent template.
  - **name** (string) - The name of the agent template.
  - **description** (string) - The description of the agent template.
  - **repo_url** (string) - The URL of the Git repository associated with the agent template.
  - **root_dir** (string) - The root directory of the agent template.
  - **required_env_vars** (array) - The required environment variables for the agent template.
  - **dependencies** (array) - The dependencies of the agent template.
  - **owner_id** (string) - The ID of the owner of the agent template.
  - **created_at** (string) - The UTC timestamp when the agent template was created.
  - **updated_at** (string) - The UTC timestamp when the agent template was last updated.

#### Response Example
{
  "templates": [
    {
      "id": "string",
      "name": "string",
      "description": "string",
      "repo_url": "string",
      "root_dir": "string",
      "required_env_vars": [
        "string"
      ],
      "dependencies": [
        "string"
      ],
      "owner_id": "string",
      "created_at": "string",
      "updated_at": "string"
    }
  ]
}
```

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

### Initialize LlmAgent with Basic Configuration

Source: https://docs.cartesia.ai/line/sdk/agents

Use the built-in LlmAgent to wrap LLM providers. Specify the model, API key, optional tools, and configuration including system prompt and introduction.

```python
from line.llm_agent import LlmAgent, LlmConfig

agent = LlmAgent(
    model="anthropic/claude-haiku-4-5-20251001",  # Or "gpt-5.2", "gemini/gemini-2.5-flash", etc.
    api_key="your-api-key",
    tools=[...],  # Optional list of tools
    config=LlmConfig(
        system_prompt="You are a helpful assistant...",
        introduction="Hello! How can I help you today?",
    ),
)
```

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

### Run Voice Update Example (TypeScript)

Source: https://docs.cartesia.ai/llms-full.txt

Clones the Cartesia JS repository, installs dependencies, and executes the voice update example. Requires a Cartesia API key and a voice ID.

```sh
git clone --branch v3.2.0 https://github.com/cartesia-ai/cartesia-js
cd cartesia-js
pnpm i
CARTESIA_API_KEY=YOUR_KEY pnpm tsn examples/node_examples.ts voicesUpdate <voice_id> "Updated Name"
```

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

### Example: Scoped knowledge_base Tool with Filters

Source: https://docs.cartesia.ai/llms-full.txt

This example configures the `knowledge_base` tool to search within a specific category ('billing') and limits the results to the top 10. It also provides a tailored description for the LLM.

```python
# Knowledge base scoped to a metadata filter with a tailored prompt
tools=[knowledge_base(
    filters={"category": "billing"},
    top_k=10,
    description="Look up billing and payment policy details.",
)]
```

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

### Run TypeScript TTS WebSocket Continuations Example

Source: https://docs.cartesia.ai/examples/tts-websocket-continuations

Clone the Cartesia JavaScript repository, install dependencies, and run the TypeScript TTS WebSocket continuations example. Ensure you set your CARTESIA_API_KEY.

```sh
git clone --branch v3.2.0 https://github.com/cartesia-ai/cartesia-js
cd cartesia-js
pnpm i
CARTESIA_API_KEY=YOUR_KEY pnpm tsn examples/node_examples.ts ttsWebsocketContinuations
```