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

# Connecting to Messaging and Voice Channels

> Check out how to make your Rasa assistant available on platforms like Facebook Messenger, Slack, Telegram or even your very own website.

<Info>
  **Installation Requirements**

  To use most channel connectors, you need to install the `channels` dependency group:

  ```bash theme={null}
  pip install 'rasa-pro[channels]'
  ```

  For more information about dependency groups, see our [Python Versions and Dependencies](/docs/reference/python-versions-and-dependencies) reference page.
</Info>

## Connecting to a Channel

### Text & Chat

Learn how to make your assistant available on:

* [Your Own Website](/docs/reference/channels/your-own-website)
* [Facebook Messenger](/docs/reference/channels/facebook-messenger)
* [Slack](/docs/reference/channels/slack)
* [Telegram](/docs/reference/channels/telegram)
* [Twilio](/docs/reference/channels/twilio)
* [Microsoft Bot Framework](/docs/reference/channels/microsoft-bot-framework)
* [Cisco Webex Teams](/docs/reference/channels/cisco-webex-teams)
* [RocketChat](/docs/reference/channels/rocketchat)
* [Mattermost](/docs/reference/channels/mattermost)
* [Google Hangouts Chat](/docs/reference/channels/hangouts)
* [Custom Connectors](/docs/reference/channels/custom-connectors)

### Voice

Learn how to build voice assistants with:

* [Audiocodes VoiceAI Connect](/docs/reference/channels/audiocodes-voiceai-connect)
* [Jambonz](/docs/reference/channels/jambonz)
* [Twilio Voice](/docs/reference/channels/twilio-voice)
* [Twilio Media Streams](/docs/reference/channels/twilio-media-streams)
* [CHIRP](/docs/reference/channels/chirp)
* [Signalwire](/docs/reference/channels/signalwire)
* [Vonage](/docs/reference/channels/vonage)
* [WebSocket Voice](/docs/reference/channels/websockets-voice)

To learn more about integration ASR and TTS engines, head over to [Speech Integrations](/docs/reference/integrations/speech-integrations).

For how Rasa spaces consecutive bot audio on voice stream channels (minimum gaps and silence between messages), see [Minimum pacing between bot messages (voice streams)](/docs/reference/config/overview#minimum-pacing-between-bot-messages-voice-streams).

Only some channels deliver assistant text incrementally. Voice stream connectors and the REST channel (with `?stream=true`) support real-time streaming when paired with a streaming-capable action executor; most messaging channels do not. See [Built-in output channels with streaming support](/docs/reference/channels/custom-connectors#built-in-output-channels-with-streaming-support).

## Testing Channels on Your Local Machine

If you're running a Rasa server on `localhost`,
most external channels won't be able to find your server URL, since `localhost` is not open to the internet.

To make a port on your local machine publicly available on the internet,
you can use [ngrok](https://ngrok.com/). Alternatively, see this [list](https://github.com/anderspitman/awesome-tunneling)
tracking and comparing other tunneling solutions.

After installing ngrok, run:

```bash theme={null}
ngrok http 5005; rasa run
```

When you follow the instructions to make your assistant available on a channel, use the ngrok URL.
Specifically, wherever the instructions say to use `https://<host>:<port>/webhooks/<CHANNEL>/webhook`,
use `<ngrok_url>/webhooks/<CHANNEL>/webhook`, replacing `<ngrok_url>` with the randomly generated
URL displayed in your ngrok terminal window. For example, if connecting your bot to Slack,
your URL should resemble `https://26e7e7744191.ngrok.io/webhooks/slack/webhook`.

<Warning>
  With the free-tier of ngrok, you can run into limits on how many connections you can make per minute.
  As of writing this, it is set to 40 connections / minute.
</Warning>

Alternatively you can make your assistant listen on a specific address using the `-i` command line
option:

```bash theme={null}
rasa run -p 5005 -i 192.168.69.150
```

This is particularly useful when your internet facing machines connect to backend servers using a VPN
interface.


## Related topics

- [Python Versions and Dependencies](/docs/reference/python-versions-and-dependencies.md)
- [Voice Assistants](/docs/pro/build/voice-assistants.md)
- [WebSocket Voice Channel](/docs/reference/channels/websockets-voice.md)
- [Jambonz as Voice Gateway](/docs/reference/channels/jambonz.md)
- [Set Up Your Agent on GCP](/docs/learn/deployment/gcp/gcp-playbook-setup-agent.md)