ElevenLabs' best-practices documentation covers pauses, emphasis and audio tags. This sheet quotes it, including the parts that come with a warning.
- There is no prompt field. The text you submit is the performance.
- Eleven v3 uses inline audio tags such as
[laughs],[whispers]and[sighs], and ElevenLabs says it does not support SSML break tags. - Other models take break tags for pauses. Use them sparingly: too many in one generation can make the output unstable.
- Punctuation does real work. ElevenLabs says ellipses add pauses and weight, and capitals add emphasis.
- A tag cannot override the voice. A whispering voice will not start shouting because of a tag; test tags on the voice you actually use.
Every rule on this sheet is quoted from the vendor's own published documentation, linked where it is used.
The formula
ElevenLabs, Best practices, read at source 16 Sep 2026.
Template:
[Sentence with ordinary punctuation for rhythm.] [Ellipsis for a weighted pause …] [CAPITALS for emphasis.] [v3: inline audio tag] / [break-tag models: <break time="1.0s" />]
Worked example:
It was a VERY long day [sigh] … nobody listens anymore.
Breakdown — what each part does
The script
Ordinary prose with deliberate punctuation. This carries most of the performance. The example above is ElevenLabs' own.
Punctuation
ElevenLabs: “Standard punctuation provides natural speech rhythm”
Capitalisation
ElevenLabs: “Capitalization increases emphasis”
v3 audio tags
Inline square brackets for emotion and delivery. ElevenLabs: “The voice you choose and its training samples will affect tag effectiveness.”
Break tags (not v3)
<break time="x.xs" />, up to 3 seconds. Dashes and ellipses also pause, but ElevenLabs adds: “However, these are less consistent.”
Does it take a negative prompt?
The nearest thing to a negative prompt here is restraint: fewer tags, not more.
ElevenLabs, Best practices, read at source 16 Sep 2026: “Using too many break tags in a single generation can cause instability. The AI might speed up, or introduce additional noises or audio artifacts.”
Write the script with punctuation first. Add a tag only where the plain reading came out wrong.
What not to do
This is this site's working order, not an ElevenLabs rule: write the script with punctuation, generate, then add tags only where the plain reading failed. Tagging every line up front is the voice equivalent of a bloated negative prompt. An earlier version of this sheet said break tags on v3 "fail silently"; ElevenLabs says only that v3 does not support them, so that wording was removed.
Free or paid? What the free plan allows, who owns the output, and when you need to pay: free vs paid AI image, video and music tools.
Where this model sits among the others: which models take a negative prompt, and what each vendor publishes as its formula.
Voice and music prompting more generally is on prompting music and voice.
The checklist
Before you send it:
ElevenLabs, Text to Speech best practices All read at source on 16 Sep 2026.
Model versions and vendor documentation both move. Re-read the source before relying on a specific number.
Every other sheet in this set: all model cheat sheets.