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

# TTS audio tags

> Direct emotion, delivery, pacing, accents, and reactions with Eleven v3 audio tags.

> [!NOTE]
>
> This is a **premium feature**. [Upgrade your plan](https://docs.brewbot.gg/getting-started/billing.md) to access it.

Audio tags are short directions in square brackets that change how the **Eleven v3** voice model speaks. Use them to add emotion, whispering or shouting, laughter, pauses, accents, and character voices to text-to-speech.

Audio tags work anywhere BrewBot reads text with the shared TTS voice:

* [TikTok Chat TTS](https://docs.brewbot.gg/features/tts.md) messages and announcements
* [Twitch TTS](https://docs.brewbot.gg/features/twitch-tts.md) messages
* [TTS Story](https://docs.brewbot.gg/features/tts-story.md) narration

## Turn on Eleven v3

1. Open **Live Tools > TTS Settings**.
2. In the **Voice** card, set the voice model to **Eleven v3**.
3. Add tags to chat messages, announcements, or story text.

With **Eleven Multilingual v2**, tags aren't performed and may be read aloud or ignored.

## How to write tags

Put a tag directly before the words it should affect. You can change direction several times in one message, even mid-sentence.

```text theme={null}
// [whispering] I have a secret. [laughs] We reached the goal!
```

* Tags use `[square brackets]`.
* Tags are written in plain English. There is no fixed list, so you can describe a delivery in your own words.
* Combine directions in one tag with commas, such as `[quietly, after a pause]` or `[angry, shouting]`.
* Tags count toward message and announcement character limits.
* A message needs spoken words besides its tags. A message made only of tags, such as `// [laughs]`, is skipped.

> [!NOTE]
>
> Tags are prompts, not guaranteed effects. Results vary by voice and by the surrounding text, and not every tag works with every voice. Test a tag with your chosen voice before relying on it live.

## Emotions

Change how the speaker feels.

| Mood | Tags |
| - | - |
| Happy and positive | `[happy]` `[happily]` `[excited]` `[cheerfully]` `[playfully]` `[curious]` `[mischievously]` `[awe]` `[surprised]` `[calm]` |
| Sad and negative | `[sad]` `[sorrowful]` `[crying]` `[angry]` `[frustrated]` `[annoyed]` `[upset]` `[regretful]` `[resigned tone]` `[disappointed]` `[bitter]` |
| Fear and nerves | `[nervous]` `[nervously]` `[hesitant]` `[panicking]` `[cautiously]` `[worried]` `[scared]` `[anxious]` `[timidly]` `[flustered]` `[exasperated]` |
| Attitude | `[sarcastic]` `[sarcastically]` `[cheeky]` `[dismissive]` `[deadpan]` `[flatly]` `[casual]` `[dramatic]` `[dramatically]` `[whiny]` `[matter-of-fact]` `[suspicious tone]` |

## Delivery and volume

Control how loud and how forcefully something is said.

`[whispers]` `[whispering]` `[quietly]` `[softly]` `[shouts]` `[shouting]` `[loudly]` `[screaming]` `[yelling]` `[understated]` `[emphasized]` `[stress on next word]` `[deliberate]` `[neutral tone]` `[deep voice]` `[robotic tone]`

## Laughter and reactions

Add laughs, breaths, and other non-verbal sounds.

| Type | Tags |
| - | - |
| Laughter | `[laughs]` `[laughing]` `[chuckles]` `[laughs harder]` `[laughs hard]` `[starts laughing]` `[big laugh]` `[giggle]` `[light chuckle]` `[laughs wickedly]` `[evil laugh]` `[wheezing]` `[snorts]` `[woo]` |
| Breathing | `[sighs]` `[sigh]` `[sighing]` `[sigh of relief]` `[exhales]` `[breathes]` `[gasps]` `[gasp]` |
| Throat and swallowing | `[gulp]` `[gulps]` `[swallows]` `[clears throat]` |

## Pacing and pauses

Shape timing for conversation or narration.

`[pause]` `[pauses]` `[long pause]` `[continues after a beat]` `[hesitates]` `[stammers]` `[rushed]` `[rapid-fire]` `[fast-paced]` `[slows down]` `[slowly]` `[drawn out]` `[repeats]` `[breathes]` `[deliberate]`

> [!TIP]
>
> Eleven v3 doesn't support SSML break tags such as `<break time="1s" />`. Use `[pause]` or `[long pause]`, or punctuation such as ellipses (`...`) and line breaks.

## Accents

Change pronunciation and speaking style without translating the words.

`[American accent]` `[British accent]` `[Australian accent]` `[Irish accent]` `[Scottish accent]` `[Southern US accent]` `[New York accent]` `[Indian English]` `[French accent]` `[German accent]` `[Spanish accent]` `[Italian accent]` `[Russian accent]` `[strong French accent]` `[thick Irish accent]`

Use the pattern `[strong X accent]` or `[thick X accent]` to try other accents.

## Character voices

Give the voice a persona or acting style.

`[pirate voice]` `[evil scientist voice]` `[childlike tone]` `[deep voice]` `[robotic tone]` `[fantasy narrator]` `[sci-fi AI voice]` `[classic film noir]` `[dramatic]` `[sarcastically]` `[matter-of-fact]` `[whiny]`

## Conversation and interruptions

Direct turn-taking when a message or story reads like a conversation.

`[interrupting]` `[overlapping]` `[cuts in]` `[interjecting]` `[jumping in]` `[starting to speak]` `[hesitates]` `[fast-paced]` `[flustered]` `[casual]`

## Sound effects

`[applause]` `[clapping]` `[gunshot]` `[explosion]` `[fart]` `[sings]` `[woo]` `[swallows]` `[gulps]`

> [!WARNING]
>
> Sound effect tags are experimental and vary a lot between voices. For a specific, repeatable sound, use [Gift Sounds](https://docs.brewbot.gg/features/gift-sounds.md) or [Sticker Sounds](https://docs.brewbot.gg/features/sticker-sounds.md) instead.

## Combined tags

Combine several directions in one tag for a more specific performance. These are starting points to experiment with, not presets.

```text theme={null}
[whispering, nervous]
[low, gravelly voice]
[angry, shouting]
[softly, sorrowful]
[excited, laughing]
[slowly, dramatically]
[sarcastic, playful]
[tired, frustrated]
[quietly, with controlled fear]
```

## Example script

This works well as a [TTS Story](https://docs.brewbot.gg/features/tts-story.md) or announcement:

```text theme={null}
[excited] Welcome to TeamBrew!

[chuckles] Oh, you thought this was going to be easy?

[whispers] Well, I've got a little secret for you...

[long pause]

[shouting] THE BATTLE STARTS NOW!

[laughs wickedly]

[calmly] Good luck. You're going to need it.
```

## Troubleshooting

| Symptom | Check |
| - | - |
| The tag is read aloud | Confirm the voice model in the **Voice** card is **Eleven v3**. Check that the tag uses square brackets, not parentheses or braces. |
| The tag has no effect | Try a different voice, a more common tag, or more text after the tag. Short messages give the model less to work with. |
| A sound effect sounds wrong | Sound effect tags are experimental. Use [Gift Sounds](https://docs.brewbot.gg/features/gift-sounds.md) or [Sticker Sounds](https://docs.brewbot.gg/features/sticker-sounds.md) for exact clips. |
| A tag-only message isn't read | Messages with no words left after removing tags are skipped. Add text after the tag. |
| A chat message with tags isn't read | Tags don't change eligibility. Check the trigger mode, `//` prefix, audience, and blocked list in [TikTok Chat TTS](https://docs.brewbot.gg/features/tts.md#troubleshooting) or [Twitch TTS](https://docs.brewbot.gg/features/twitch-tts.md). |


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.