Back to results
Explore the library298 guides total · goals, work & tasks
By goal

Choose what you want to achieve.

By work or interest

Choose a setting you work or spend time in.

By task

Choose the kind of help you want.

Counts show all available guides. Filters combine to narrow your results.

Launch somethingGuide

Write a scene that works without pictures

Use voices and clear sound cues to tell a small story a listener can follow.

Illustrative resourceNot tool-testedAnyone starting a personal creative project
What you’re working towards

Use voices and clear sound cues to tell a small story a listener can follow. The worked result was written for this guide; it is not a recording of an AI run.

Download playbook .md

Your choice also saves this guide’s current worked-example checkmarks. Only this browser; no account or sync. View saved guides

Saving needs JavaScript. Reading and downloading this guide does not save it.

Make a start

One step at a time.

3 steps

Start with the synthetic worked example or other non-sensitive inputs. Run one prompt at a time in your chosen AI tool. Replace any bracketed placeholders with the requested material, check each reply, and supply the source or earlier outputs that step needs. Paste them again if the tool lacks that context.

Start with the synthetic example, then adapt each prompt to your task.

01

Open a text assistant and try the example

For a concrete starter route, open https://chatgpt.com and choose New chat. Sign in if that service requires it for your access. You can also use another text assistant you already have. Copy the entire prompt below (the instructions to paste), including the sample input, into its message box and send it. No upload or image generation is needed. Expect a complete two-voice script with performable sound cues. The wording may differ from the example; the constraints should not. If it only explains the task, ask it to produce the finished result using the supplied input.

Your starting prompt
Write a short audio-only script with the two supplied speaking roles. Use speaker names and bracketed sound cues. Include an audible reason for the characters to be where they are and let the reveal be understandable without sight. Keep the story gentle. Do not add background music or other music beyond the specified brief original music-box notes; do not add a narrator or third voice.

Use this complete made-up practice input:
Characters: Adult repair-shop owner Fenn and adult customer Ora.
Situation: Ora brings a small wind-up music box because she thinks it is silent. The lid is stuck; when Fenn opens it carefully, the mechanism plays a few notes. The actual tune is not specified and must not quote a real song.
Allowed sound cues: Door bell, box set on a counter, soft lid creak, brief original wordless musical notes from the box.
Required spoken facts: Ora brought a music box; it has not played for her; the lid is stuck; opening the lid lets it play.
Boundaries: No actual repair instructions, dangerous tools, money, promised repair guarantee or copyrighted song lyrics. End with Ora recognizing the sound.
Deliverable: Written script only, not generated audio.

Return the finished result. Keep it fictional and do not add claims about real people, products or events.
02

Check, correct and save

Read the response beside the original input. Find only two speaking roles and the four allowed kinds of sound. Check a listener can identify the music box, stuck lid and audible result without seeing them. Confirm no actual repair method or real melody is supplied. If a check fails, paste the correction prompt below in the same conversation. Check the revised result yourself, then copy the version you want into your own notes or document.

Your starting prompt
Check your previous result against this original input:
Characters: Adult repair-shop owner Fenn and adult customer Ora.
Situation: Ora brings a small wind-up music box because she thinks it is silent. The lid is stuck; when Fenn opens it carefully, the mechanism plays a few notes. The actual tune is not specified and must not quote a real song.
Allowed sound cues: Door bell, box set on a counter, soft lid creak, brief original wordless musical notes from the box.
Required spoken facts: Ora brought a music box; it has not played for her; the lid is stuck; opening the lid lets it play.
Boundaries: No actual repair instructions, dangerous tools, money, promised repair guarantee or copyrighted song lyrics. End with Ora recognizing the sound.
Deliverable: Written script only, not generated audio.

Check these requirements one by one:
- Find only two speaking roles and the four allowed kinds of sound.
- Check a listener can identify the music box, stuck lid and audible result without seeing them.
- Confirm no actual repair method or real melody is supplied.
Quote each problem, explain the smallest repair, and return a complete corrected version. If there is no problem, say which checks you applied. Do not claim that your own review proves quality or audience response.
03

Optional: use your own material

Open a new chat. Copy the prompt below and replace [PASTE YOUR INPUT HERE] with two fictional speaking roles, situation, allowed sound cues, facts the listener must hear and exclusions. Use material you own or may use and leave out private details. The output limits written in this prompt stay in force; change a limit here too if you want a different one. Send the whole message. Expect the same kind of written result with your new material. Check it against this new input and these limits, not the sample’s names or numbers. If it differs, describe the exact mismatch and ask for a complete correction before saving.

Your starting prompt
Write a short audio-only script from my input below, with the two supplied speaker names and bracketed sound cues. Make the situation and reveal understandable without sight. Use only the allowed sounds, with no narrator, third voice or extra music. Do not quote real song lyrics or provide repair instructions. This is a written script, not generated audio.

If an essential detail is missing or two requirements conflict, ask me before filling the gap.

MY INPUT
[PASTE YOUR INPUT HERE]
Optional: improve the result

Rehearse clarity with fewer explanations

Reduce exposition only after preserving what a listener needs. Keep the first version so you can compare the change. This extension uses the worked example. Return to that example chat, or paste its input and your checked example answer into a new chat first. Do not apply its sample values unchanged to your own input.

Advanced prompt
Make a second version with two fewer spoken lines. Preserve every required fact and the final recognition. Identify which information is carried by sound and which still needs speech. Do not add a narrator or real song.
Use the original input and result in this conversation. If either is missing, ask me to paste it before continuing.
Show, then try

See the shape of the result.

This input is synthetic. The output is a written illustration of the intended result, not a verified AI-tool run.

The starting point

Synthetic input
Made-up example for practice. All people, places and events are invented.

Characters: Adult repair-shop owner Fenn and adult customer Ora.
Situation: Ora brings a small wind-up music box because she thinks it is silent. The lid is stuck; when Fenn opens it carefully, the mechanism plays a few notes. The actual tune is not specified and must not quote a real song.
Allowed sound cues: Door bell, box set on a counter, soft lid creak, brief original wordless musical notes from the box.
Required spoken facts: Ora brought a music box; it has not played for her; the lid is stuck; opening the lid lets it play.
Boundaries: No actual repair instructions, dangerous tools, money, promised repair guarantee or copyrighted song lyrics. End with Ora recognizing the sound.
Deliverable: Written script only, not generated audio.

Copies text only. For image or file tasks, use the source files named in the steps too.

Download source .txt

The intended result

Illustrative output
Worked example written for this guide; it is not a recording of an AI run.

THE QUIET BOX

[SOUND: A small door bell.]

FENN: Come in. What have you brought?

ORA: A wind-up music box. It hasn't played for me once.

[SOUND: The box is set on the counter.]

FENN: This little one?

ORA: Yes. I turn it over, wait, try again. Nothing.

FENN: And the lid?

ORA: It won't open. I thought that was a separate problem.

FENN: The lid is stuck. Let's give it a moment.

[SOUND: A soft lid creak.]

ORA: Oh. You've opened it.

[SOUND: A few brief, original wordless musical notes from the box.]

FENN: There it is. Opening the lid lets it play.

ORA: Wait—let me hear that again in my head.

[PAUSE. No new sound cue.]

ORA: Yes. That's the sound I was hoping for.

End. This is a written performance script; no recording or mechanical repair has been carried out.
Download result .txt
You’re the final check

Check the worked example.

These checks use the worked example and its particular facts. With your own material, check your actual names, numbers, sources and rules; do not reuse the sample’s values as the answer.

Unsaved checks stay in this tab and reset when you reload. If you choose Save guide, its current example checkmarks are kept in this browser when storage is available.

A few things to watch for.

  • Visual stage directions do not help an audio listener unless they create an audible effect. Translate essential information into speech or sound.
  • Sound cues are production instructions, not generated audio. A real recording still needs performance and listening checks.

What has been checked?

Documentation
No dated source review recorded.
Included files
No scoped artifact-check record.
AI workflow
Not run in a recorded consumer-AI workflow.
Time savings
Time savings not measured

Copy these instructions

Your browser blocked automatic copying. Select the text below and copy it.