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

# Twitch TTS

> Read Twitch chat messages aloud on stream with text-to-speech powered by ElevenLabs.

<Info>
  This is a **premium feature**. [Upgrade your plan](/getting-started/billing) to access it.
</Info>

Twitch TTS reads messages from a Twitch channel's chat and plays them as spoken audio on your stream using ElevenLabs voices. It runs independently from [Chat TTS](/features/tts) (TikTok) — each has its own overlay, settings, and queue.

Configure Twitch TTS from the **Twitch TTS** tab on the TTS settings page in the dashboard.

## Set up Twitch TTS

<Steps>
  <Step title="Open TTS settings">
    Go to the [BrewBot Dashboard](https://brewbot.gg), select your server, and navigate to **Live Tools → TTS Settings**. Select the **Twitch TTS** tab.
  </Step>

  <Step title="Add a Twitch channel source">
    Search for the Twitch channel by username and add it. This tells BrewBot which chat to monitor for TTS messages.
  </Step>

  <Step title="Connect the source">
    Click **Connect** to start the Twitch OAuth flow. You'll be redirected to Twitch to authorize BrewBot to read chat messages from the channel.

    <Note>
      After authorizing, the source status updates to **Connected**. If something goes wrong, the status shows **Error** — try disconnecting and reconnecting.
    </Note>
  </Step>

  <Step title="Select the active source">
    Choose the connected source as the active Twitch channel for TTS. Only one source can be active at a time.
  </Step>

  <Step title="Configure settings">
    Set your preferred trigger mode, audience level, and voice options. See the sections below for details on each setting.
  </Step>

  <Step title="Enable Twitch TTS">
    Toggle Twitch TTS on. The bot starts listening to the connected Twitch channel's chat.
  </Step>
</Steps>

***

## Add the overlay to your stream

Twitch TTS plays audio through a **browser source overlay** in your streaming software (OBS, Streamlabs, etc.).

<Steps>
  <Step title="Copy the overlay URL">
    In the Twitch TTS settings, copy the **overlay URL**. It looks like this:

    ```text theme={null}
    https://brewbot.gg/overlay/twitch-tts/{serverId}?token={your-token}
    ```

    Each server gets a unique secure token. Do not share this URL publicly — anyone with the link can connect to your TTS feed.
  </Step>

  <Step title="Add a browser source in OBS">
    In OBS (or your streaming software), add a new **Browser Source**:

    1. Click **+** in the Sources panel.
    2. Select **Browser**.
    3. Name it something like `Twitch TTS`.
    4. Paste the overlay URL into the **URL** field.
    5. Set the width and height to any value (the overlay is invisible — it only plays audio).
    6. Make sure **Control audio via OBS** is unchecked so the audio plays through your stream.
  </Step>

  <Step title="Test the overlay">
    Send a TTS-eligible message in the connected Twitch channel's chat to confirm audio plays through your stream.
  </Step>
</Steps>

<Warning>
  If you regenerate your overlay token in the dashboard, the old URL stops working. Update the browser source URL in OBS with the new token.
</Warning>

***

## Trigger modes

| Mode             | Behavior                                                           |
| ---------------- | ------------------------------------------------------------------ |
| **Prefix**       | Messages must start with `//` to trigger TTS. This is the default. |
| **All messages** | Every eligible message is read aloud — no prefix needed.           |

<Tip>
  In Prefix mode, you can enable **Allow privileged bypass** so that broadcasters, moderators, and VIPs can trigger TTS without the `//` prefix.
</Tip>

***

## Audience controls

Control who can trigger Twitch TTS:

| Level              | Who can trigger TTS               |
| ------------------ | --------------------------------- |
| **Staff Only**     | Broadcaster and Moderators        |
| **VIPs and Staff** | VIPs, Broadcaster, and Moderators |
| **VIPs Only**      | VIPs and Broadcaster              |
| **Everyone**       | Any chatter                       |

You can further refine access with two lists:

* **Whitelist** — specific Twitch usernames that can always trigger TTS, regardless of the audience level. When the whitelist has entries, only whitelisted users and privileged users (broadcaster, mods, VIPs) can trigger TTS.
* **Blocklist** — specific Twitch usernames that are always blocked from triggering TTS, even if they are on the whitelist.

<Note>
  Override precedence: **Blocklist > Whitelist > Audience level**. A blocked user cannot trigger TTS under any circumstances.
</Note>

***

## Voice settings

| Setting         | Default         | Description                                                                                             |
| --------------- | --------------- | ------------------------------------------------------------------------------------------------------- |
| **Voice mode**  | Single          | **Single** uses the same voice for every message. **Random All** picks a random voice for each message. |
| **Voice model** | Multilingual v2 | Choose **Multilingual v2** for stable general-purpose speech, or **v3** for audio tag support.          |
| **Voice**       | —               | Select from the available ElevenLabs voices.                                                            |

<Card title="Audio tags and voice models" icon="volume" href="/features/tts">
  Full reference for ElevenLabs audio tags, voice models, and layering techniques.
</Card>

***

## Source management

You can add multiple Twitch channel sources, but only **one source can be active at a time**. Use the source library to:

* **Add** a new Twitch channel by searching for the username
* **Remove** sources you no longer need
* **Connect / Disconnect** OAuth per source — reconnect if the connection drops or the token expires
* **Enable / Disable** individual sources

Each source shows two statuses:

| Status type    | Values                                     |
| -------------- | ------------------------------------------ |
| **Connection** | Disconnected, Connecting, Connected, Error |
| **Auth**       | Disconnected, Pending, Connected, Error    |

<Warning>
  If a source shows **Error** status, disconnect it and reconnect through the Twitch OAuth flow. The token may have expired or been revoked.
</Warning>

***

## Queue management

Pending TTS jobs appear in the queue on the dashboard. You can:

* **View the queue** — see pending and claimed jobs with sender info and message text
* **Clear the queue** — remove all pending jobs at once
* **Regenerate overlay token** — create a new secure overlay URL (the old URL stops working immediately)

***

## FAQ

<AccordionGroup>
  <Accordion title="What is the difference between Twitch TTS and Chat TTS?">
    Twitch TTS reads messages from a Twitch channel's chat. [Chat TTS](/features/tts) reads messages from TikTok live chat. They are separate systems with their own overlays, settings, and queues.
  </Accordion>

  <Accordion title="Can I use both Twitch TTS and Chat TTS at the same time?">
    Yes. They run independently. Each has its own overlay URL — add them as separate browser sources in OBS.
  </Accordion>

  <Accordion title="Why does my Twitch source show an Error status?">
    The OAuth token may have expired or been revoked on the Twitch side. Disconnect the source and reconnect through the Twitch authorization flow to get a fresh token.
  </Accordion>

  <Accordion title="Do audio tags work with Twitch TTS?">
    Yes, if you select the **v3** voice model. See the [audio tags reference](/features/tts#audio-tags) on the TTS page for the full list of supported tags.
  </Accordion>
</AccordionGroup>