Audio tags are inline tokens you put in the input text to make speech expressive: laughs,
sighs, breaths, pauses, and emotional delivery. They work everywhere — the playground, the
HTTP API, and the streaming WebSocket. In the playground, the Enhance button inserts
them for you automatically.
There are two kinds of tags, with two different shapes.
An event tag is a bare token followed by a space. It inserts one sound (a laugh, a sigh, a
cough…) at that point in the speech.
Supported events
Placement
- Lead the sentence: laugh, chuckle, giggle, laugh_harder, hum_tune, woo, yawn,
throat_clear, exhale, sigh, inhale, tsk, cough, cry, sniff.
- Between clauses (mid-sentence): breath, long_pause, clap, gulp, snort, lip_smack,
tongue_click.
- Either slot: pause, gasp.
Onomatopoeia pairing (strongest effect)
Pair a voiced event with its sound word for the most convincing result; the bare token alone
gives a subtler effect:
Breath types (breath, inhale, exhale, sigh, pause, long_pause) are always used
bare — no sound word.
<|snort|> is a derisive snort (“pfft”), not a nasal sniff — use <|sniff|> for nasal.
Style wraps — color a whole sentence
A style wrap sets the emotional delivery of one full sentence:
To change style, close the current wrap and open a new one back-to-back:
Supported styles
Emotions:
Accents:
If the feeling you want isn’t listed (serious, monotone, fast, slow…), leave the sentence
untagged — neutral is the correct default. Nearest matches: warm/gentle/soft → tender,
happy → joyful, quietly/whisper → whispers, interested → curious, concerned/tense →
nervous, impressed → awe, terrified → fearful.
Rules of thumb
- Use the exact tokens — no spaces inside
<|…|>, and only the tags listed here.
Don’t invent tags (<|singing|>, <|music|> etc. are not supported).
- At most one style per sentence, and a style never carries past
<|style_close|>.
- Tags describe the voice only — no music, sound effects, or physical actions.
- Add emphasis with a CAPITAL word,
? / !, or … ellipses rather than piling on tags.
- Pick tags that match the line’s emotion; a contradicting tag sounds worse than none.
Full example
Input text:
My uncle thought the robot vacuum was a cat and fed it milk. I couldn’t stop laughing.
Then I got worried it might break.
Tagged: