Convert my raw script into a voiceover-ready script formatted for ElevenLabs / Play.HT / OpenAI TTS so it actually sounds human.
RAW SCRIPT:
```
{paste_your_script}
```
TONE I WANT: {warm_narrator / energetic_explainer / quiet_intimate / authoritative_documentary}
AUDIENCE & USE: {YouTube_explainer / app_onboarding / podcast_intro / audiobook_chapter}
LENGTH I'M TARGETING: {seconds_or_words}
REWRITE THE SCRIPT WITH:
1. **Sentence-level pauses** marked as `<break time="0.5s" />` (ElevenLabs syntax). Pause 0.3-0.6s after declarative sentences, 0.8-1.2s after rhetorical shifts, 1.5s before key reveals.
2. **Emphasis cues** using ALL CAPS for words to stress (1-2 per paragraph max). TTS engines push slight inflection on these.
3. **Sentence length variation.** Mix 5-word sentences with 15-word sentences. AI voices sound robotic on uniform sentence length.
4. **Contractions where natural** ('it is' → 'it's'). TTS handles these better than the long form.
5. **No tongue-twister cluster consonants** ('rugged red roof rebuilds' = avoid). If the original has them, rewrite the line.
6. **Read-the-numbers conversion.** '$1,250' → 'twelve hundred and fifty dollars' OR keep as-is, but pick one and stay consistent.
OUTPUT:
- **Original script length:** X words
- **Voiceover-ready script:** [paste with markup]
- **Estimated duration:** Y seconds at 165 wpm
- **3 lines flagged for re-take:** [lines TTS will likely mispronounce or stumble on]0 copies·0 saves·1 views
205 words·1,452 chars
Sample output
Original script length: 92 words.
Voiceover-ready script:
Most people think AWS bills get out of control because of usage. They don't.
They get out of control because of FORGOTTEN resources. A test EC2 instance from six months ago. An old S3 bucket nobody's touched since 2022. Quiet, idle, expensive.
Last weekend I found four of them. Together they were costing me eleven HUNDRED dollars a month.
So here's what I want to show you. An audit you can run in thirty minutes. No new tools. No consultants.
Let's start with the easiest one first.
Estimated duration: ~42 seconds at 165 wpm.
3 lines flagged for re-take:
<break time="0.2s" /> between 'months' and 'ago'.Parameters
Text generation parameters
FAQ
Don't over-mark pauses. More than ~3 breaks per sentence will make the voice sound mechanical. The natural rhythm comes from contractions + sentence length variation more than explicit pause tags. The prompt targets ChatGPT (GPT-4) and lives in the Writing & Content category on mycopyprompt.
This prompt is written for ChatGPT (GPT-4). It's a text/chat prompt — paste it into ChatGPT (GPT-4) (or compatible LLMs like Claude or GPT-4) to get the expected output.
1. Click the Copy button on this page to copy the full prompt. 2. Open ChatGPT (GPT-4). 3. Paste the prompt into a new conversation. 4. Replace any {placeholders} with your specifics, then send. Most prompts produce the right output on the first try; complex ones may need 1-2 iterations.
Yes — every prompt on mycopyprompt is free forever. No paywall, no signup wall for browsing or copying. You can use it for personal or commercial work, just don't redistribute the entire mycopyprompt library.
Absolutely — most prompts are templates. Look for {placeholders} (curly braces) and swap them with your own values. You can also reword sections, add constraints, or chain it with other prompts.
See the "Sample output" panel above — that's a real example of what ChatGPT (GPT-4) returns when this prompt runs. Your output will vary in wording but should follow the same structure and depth.
Similar prompts
Matched against every prompt in the catalog by title.