Prepare readable cue blocks before narration

Text to Speech Script Formatter

Split prose into bounded cue blocks, add optional pause markers or blank lines, and apply a speaker label for text-to-speech preparation or human narration rehearsal. The tool formats a script only: it does not synthesize audio, validate SSML, predict pronunciation, set voice emotion, or estimate provider-specific billing.

01Private by designYour text stays in this browser tab.
02Bounded and responsiveUp to 250,000 characters for bounded local analysis.
03Ready to reuseCopy the result or download a branded TXT file.

No text upload to Nirmion

Counting and transformations run locally. Nirmion does not send the text in this workspace to an API.

01 / Input

Add prose and choose the cue rhythm

Paste complete spoken wording, choose five to forty words per cue, select a pause presentation, and optionally add one speaker label. Formatting is limited to 250,000 characters and preserves source wording while changing line and cue boundaries.

Spoken scriptPaste approved spoken wording up to 250,000 characters.0 / 250 000 charactersMaximum words per cueEnter a whole number from 5 to 40.Pause presentationChoose how cue boundaries should appear in plain text.Optional speaker labelRepeat one label before every cue, or leave empty.0 / 80 characters

Complete the required fields to enable this action.

Runs in this tab without an API request.

Product guide

Format for rehearsal before choosing a voice engine

Short cue blocks make scripts easier to scan, rehearse, annotate, and move into a provider, but actual speech timing still depends on voice, language, punctuation, and delivery. Review the complete result in its destination because automated text rules cannot infer every language, house style, data model, or publishing intention.

Step A

Prepare the input

Use final spoken words rather than visual-only labels. Expand abbreviations and verify names separately when the selected speech engine may pronounce them incorrectly.

Step B

Choose the rule

Words-per-cue sets a maximum chunk size after sentence segmentation. Pause style inserts blank lines, a plain [pause] marker, or no extra separation.

Step C

Review the output

Read the formatted script aloud, confirm pronunciation and pacing, then adapt markers to the exact syntax accepted by the chosen speech or editing system.

How it works

Sentence-first chunking with plain-text pause cues

Likely sentence segments are split into whitespace-delimited words and chunked at the requested maximum. An optional speaker prefix is repeated on each cue. Pause mode joins cues with blank lines, a literal bracketed marker, or a single line break; source words are not summarized or rewritten. Input is capped at 250,000 characters, cue size at five to forty words, and the output remains plain text rather than executable SSML. The operation runs in this browser tab, applies explicit bounds before expensive work, and does not send workspace text to a Nirmion API.

Useful when

Prepare scripts for voice production

Use cue formatting to improve rehearsal and handoff while keeping provider-specific decisions explicit and separate.

Break onboarding, lessons, explainers, announcements, accessibility narration, or product demos into scan-friendly cues.
Create a presenter copy with repeated speaker labels and visible pause locations for collaborative review.
Estimate cue density before moving approved wording into a text-to-speech provider or recording workflow.

Questions answered

Text to Speech Script Formatter questions

Practical boundaries matter with text tools. These answers explain what is measured, what is retained, and when a manual review is still needed.

Does this create audio?

No. It creates a plain-text cue script that can be rehearsed or adapted for a separate audio system.

Is [pause] valid SSML?

No guarantee is made. It is a human-readable marker and may need replacement with provider-specific SSML or timeline instructions.

Does it preserve every word?

Yes. The formatter changes whitespace, cue grouping, and optional labels; it does not summarize or paraphrase source wording.

Privacy and retention

Your draft stays on your device.

Nirmion performs these operations with browser JavaScript. The workspace does not call the catalogue API with your source text, and completed-job content is kept only in this component memory for re-download.

A downloaded file remains in your browser downloads, device storage, backups, and any location where you share it. Clear or close the page when working on a shared device, and avoid pasting secrets into extensions or third-party clipboard managers.

Tool details

A private cue formatter before text-to-speech production

Nirmion Text to Speech Script Formatter converts approved prose into sentence-aware cue blocks with a configurable five-to-forty-word maximum. Optional blank-line or marker pauses and speaker labels support narration rehearsal, production handoff, and provider preparation without generating audio. Likely sentence segments are split into whitespace-delimited words and chunked at the requested maximum. An optional speaker prefix is repeated on each cue. Pause mode joins cues with blank lines, a literal bracketed marker, or a single line break; source words are not summarized or rewritten. This makes the behavior inspectable and repeatable instead of presenting an unexplained result.

The script downloads as text_nirmion_tools_tts_script.txt for input up to 250,000 characters. The page distinguishes readable pause markers from SSML and documents that voice timing, pronunciation, billing, and engine behavior require destination testing. The operation runs in this browser tab, applies explicit bounds before expensive work, and does not send workspace text to a Nirmion API. Downloading clears the active workspace while the latest three completed results remain available in this tab for re-download.