> For the complete documentation index, see [llms.txt](https://docs.nlx.ai/platform/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.nlx.ai/platform/nlx-platform-guide/integrations/types.md).

# Types

Integrations extend what your NLX AI apps can do. From how they communicate with users, to how they understand language, generate outputs, and connect to your business systems. Each type of integration unlocks different capabilities.

Select a type that fits your use case to get started or explore below for a full overview of all integration categories in NLX and what they’re used for:

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>LLM services (BYOK)</strong></td><td>How your app reasons, generates responses, and powers agentic behaviors</td><td><a href="/pages/Y61nxwpo4eBZfy5MTgMM">/pages/Y61nxwpo4eBZfy5MTgMM</a></td></tr><tr><td><strong>Managed integrations</strong></td><td>Prebuilt integrations for popular SaaS and enterprise tools</td><td><a href="/pages/JHPipw3tIdFTQmjnqAzw">/pages/JHPipw3tIdFTQmjnqAzw</a></td></tr><tr><td><strong>Custom integrations</strong></td><td>Your own APIs, services, and bespoke endpoints</td><td><a href="/pages/-McB9soNWA_EKo8ODIAh">/pages/-McB9soNWA_EKo8ODIAh</a></td></tr></tbody></table>

### Channels

Channel integrations allow your AI application to send and receive messages through external communication platforms. These define the delivery surface for conversations: chat, voice, phone/IVR, social, mobile, and more.

Use channel integrations when you want your application to run on a specific platform.

{% hint style="info" %}
Did you know? Every NLX app includes a built-in API channel with native Voice channel (for web/mobile via Touchpoint).
{% endhint %}

Examples:

* Amazon Connect
* Alexa
* Twilio
* Slack
* Zendesk Sunshine

### NLP engines

NLP engine integrations provide the natural-language understanding needed for classic intent-based routing and structured flows. These engines classify user intents and extract values that your flows rely on.

Use NLP engines when you want deterministic language understanding and flow invocation.

{% hint style="info" %}
Did you know? NLX includes a native NLP engine with optional NLX Boost, so you can handle intent recognition, language disambiguation, and app builds without needing an external NLP (unless you prefer to bring your own).
{% endhint %}

Examples:

* Amazon Lex
* Google Dialogflow
* Custom NLP

### LLM services

LLM integrations provide generative AI capabilities for messaging, decision-making, summarization, tool use, and NLX’s Generative Journey®. These models enable flexible, contextual reasoning beyond traditional NLU.

Use LLM services when you want AI-driven logic, semantic generation, retrieval, or agentic task completion.

{% hint style="info" %}
Did you know? NLX provides a built-in generative model for flows and agentic Generative Journey, so you can optionally integrate an external LLM.
{% endhint %}

Examples:

* OpenAI
* Anthropic
* Google Vertex AI
* Cohere
* Cerebras

### Managed integrations

Managed data requests provide ready-made connectors maintained by NLX. These remove setup complexity and allow you to instantly bring external systems into your flows or agentic tools, like calendars, CRMs, productivity suites, marketing platforms, and more.

Use managed integrations when you want fast reliable access to common third-party tools without custom development.

Examples:

* HubSpot
* Google Workspace
* Airtable
* Zendesk
* Shopify
* Snowflake

### Custom integrations

Custom data requests allow you to integrate any external system by defining your own webhook or API models. You control authentication, payloads, schemas, and environments, making this ideal for internal business logic or bespoke services.

Use custom integrations when you need NLX to call your own APIs or private systems not covered by a managed provider.

Examples:

* Internal scheduling APIs
* CRM or user profile services
* Custom databases
* Proprietary workflows

### Text-to-speech (TTS)

TTS integrations synthesize spoken responses for any voice-based experience, including Voice+™, phone/IVR, and voice chat. These providers let you select language, persona, tone, and attributes.

Use TTS providers when your app needs natural-sounding or brand-aligned voice output.

{% hint style="info" %}
Did you know? NLX provides five built-in TTS providers for its native voice channel, so you can skip the time to integrate.
{% endhint %}

Examples:

* Inworld
* ElevenLabs
* Hume
* Amazon Polly


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.nlx.ai/platform/nlx-platform-guide/integrations/types.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.