Home/Blog/How to Write an ElevenLabs Voice Script with SSML Pauses
Blog

How to Write an ElevenLabs Voice Script with SSML Pauses

P
promptstudio
How to Write an ElevenLabs Voice Script with SSML Pauses

Voice scripts invent celebrity clones and voice UUIDs. Style was warm and clear. Keep person names out.

The matching generator is the ElevenLabs Voice Script with SSML Pauses from a Brief (No Celebrity Voice) (Elevenlabs Voice Script With Ssml Pauses From A Brief No Celebrity Voice) prompt. Browse related cards in the PromptDig library (Browse more prompts). When a filled run survives, share the version you actually use (Share a prompt).

Draft under Seconds before SSML

Write an ElevenLabs voice script with SSML pauses from a brief. No celebrity voice cloning and no invented voice IDs. Start by filling Inputs, not by asking the model to remember last week's run. If a field is blank, write NONE or NOT IN INPUTS and leave it blank through Generate. The card is built so the model cannot honestly invent a number, owner, URL, or command that you did not paste.

Paste these fields before you hit run:

Script brief: [Brief]
Max spoken seconds I target: [Seconds]
SSML tags I allow: [SSML]
Voice style adjectives (not a person name): [Style]
Words I must not use: [Banned]
What I must never invent: [Never]
Pronunciation hints I may use: [Pronounce]
Output format: [Format]
Call-to-action line: [CTA]
Language: [Lang]

That inventory is the honesty ledger. Anything that does not appear there is forbidden in the draft. If you catch yourself adding a nice-to-have after the run, you are no longer using the card. You are ghostwriting. Put the extra fact in Inputs and run again.

Break tags only from the allow list

Generate is numbered on purpose. Do not skip a step because the first paragraph looked done. The early steps exist to stop later prose from smuggling claims.

Walk the Generate list in order:

  1. Honesty ledger: Brief, Seconds, SSML, Style, Pronounce, CTA, Lang. Forbidden: celebrity names as voices, voice IDs invent.
  2. Draft script from Brief under Seconds estimate (words/150 wpm rough only if user accepts; else count words).
  3. Insert SSML breaks only from allowed SSML tags.
  4. Style line as adjectives, never a celebrity.
  5. Pronounce list only from Pronounce.
  6. CTA at end if given.
  7. Refuse: clone celebrity, invent voice UUID.
  8. Compliance pass: cut Banned and Never. Format as Format.

If a step asks for a version lock, quote the version from Inputs in the output. If a step asks for a refuse list, keep the refuse list in the published artifact, not in a sidebar you delete. Reviewers should see what the model was not allowed to do.

Pronounce hints only as pasted

Most failures are the same shape: a missing field gets a confident fill. A conversion rate appears. A Gradle task appears. A flash point appears. A caption appears on a job that asked for slide text only. Your review is to search the draft for numbers, names, and commands, then grep Inputs. No match means cut.

Honor the constraints as hard stops, not vibes:

  • ElevenLabs script with SSML pauses. Not celebrity cloning.
  • Never invent voice IDs or celebrity likeness.
  • Only SSML tags listed in SSML.
  • No emojis.

When the card says not legal advice, not certification, not an exam dump, or not a caption engine, that sentence belongs at the top of the output. Deleting it to look more finished is how you inherit risk.

No celebrity voices

Finish with the compliance pass the prompt already asks for. Quote the banned-word hits. Cut them. Print character counts when the job has a cap. Print word counts when the job has a budget. List gaps as gaps. Five missing facts are more useful than one smooth paragraph.

Tags on the card (elevenlabs voice script ssml, ssml pauses voice script, no celebrity voice) are a reminder of the job shape, not an invitation to wander into a neighboring cluster. If you need a different surface, open a different PromptDig card rather than stretching this one.

Fill the card, then run

Replace every bracket. Run on ChatGPT, Claude, or Gemini. Read the ledger first, then the artifact. If the model invents a commit, KPI, DOI, PEL, bid, or logo, discard the run. Tighten Inputs. Run again. Share the filled card that survived, not the first draft that sounded done.