> ## Documentation Index
> Fetch the complete documentation index at: https://docs.slng.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Overview

> Ways to integrate SLNG into your stack: the CLI and SDKs, agent skills, framework plugins, and voice-platform bridges.

There are several ways to bring SLNG speech to text, text to speech, and the
Context Router into your stack. Pick the one that matches how you already build.
Every option calls the same API, so you can mix them and switch later: prototype
with the CLI, ship on a plugin, and script the rest from a notebook.

## Build with the API

Call the API directly from a terminal, a service, or a notebook. Best when you
own the code and want full control.

<CardGroup cols={3}>
  <Card title="CLI" icon="square-terminal" href="/integrations/sdks/cli">
    `voiceai` runs speech from a terminal and manages agents and other resources. Good for scripts and CI.
  </Card>

  <Card title="JavaScript SDK" icon="js" href="/integrations/sdks/js">
    `voiceai-sdk` on npm. A typed client for Node, Bun, and Deno.
  </Card>

  <Card title="Python SDK" icon="python" href="/integrations/sdks/python">
    `voiceai-sdk` on PyPI. Sync and async clients for Python 3.9+.
  </Card>
</CardGroup>

## Hand it to a coding agent

Let a coding agent like Claude Code write the integration for you, or migrate an
existing project onto SLNG.

<CardGroup cols={2}>
  <Card title="Agent skills" icon="sparkles" href="/integrations/skills/agent-skill">
    Teach a coding agent to call the API: speech, transcription, and voice agents.
  </Card>

  <Card title="Migration skills" icon="arrow-right-left" href="/integrations/skills/integrate-skill">
    Move a LiveKit, Pipecat, or custom agent onto SLNG hosted models.
  </Card>
</CardGroup>

## Add to an existing agent

Already running a voice agent on a framework? Swap its speech models for SLNG and
keep the rest of your pipeline.

<CardGroup cols={3}>
  <Card title="LiveKit" icon="https://mintcdn.com/slng-new-docs/fgzHSTXC7k7AhIuF/images/providers/livekit.svg?fit=max&auto=format&n=fgzHSTXC7k7AhIuF&q=85&s=e53c2d53e583f755d2d8245d3f6ff051" href="/integrations/plugins/livekit" width="256" height="256" data-path="images/providers/livekit.svg">
    The `livekit-plugins-slng` adapter for LiveKit Agents.
  </Card>

  <Card title="Pipecat" icon="https://mintcdn.com/slng-new-docs/fgzHSTXC7k7AhIuF/images/providers/pipecat.svg?fit=max&auto=format&n=fgzHSTXC7k7AhIuF&q=85&s=1b96dea4b4529733e291debc612674f2" href="/integrations/plugins/pipecat" width="80" height="80" data-path="images/providers/pipecat.svg">
    The `pipecat-slng` STT and TTS services for Pipecat pipelines.
  </Card>

  <Card title="n8n" icon="https://mintcdn.com/slng-new-docs/fgzHSTXC7k7AhIuF/images/providers/n8n.svg?fit=max&auto=format&n=fgzHSTXC7k7AhIuF&q=85&s=53b6c08b97dec1f9cb46131b3ffb2790" href="/integrations/plugins/n8n" width="228" height="120" data-path="images/providers/n8n.svg">
    The `n8n-nodes-slng` community node for visual automations.
  </Card>
</CardGroup>

## Your SLNG key

Every tool reads its key from an environment variable. Create one at
[app.slng.ai](https://app.slng.ai/api-keys), or see
[Create your API key](/guides/get-started/quickstart#create-your-api-key),
then export it before running the examples.

```bash theme={null}
export VOICEAI_API_KEY="slng_cu_..."
```

<Note>
  The CLI reads `VOICEAI_API_KEY`. The JavaScript and Python SDKs default to
  `SLNG_API_KEY` but accept an explicit `apiKey` option. Set both to the same
  value if you plan to use several tools side by side.
</Note>

## Model identifiers

Every tool takes the same model identifier format, `provider/family:version-lang`.
Prefix with `slng/` to target an SLNG-hosted, in-region model
(`slng/deepgram/nova:3-en`); a bare `provider/model` is the external or BYOK
route proxied through SLNG on your own `provider_key`. Browse the current models
in the [catalog](/models/catalog/all-models).