skills.rest
gooseworks-ai
gooseworks-aiOFFICIAL
Explore all skills by this author →
WebsiteGitHub

format-script-to-style

Convert unformatted scripts into v3-tagged voice scripts with specified style and duration.

6|1|Updated May 29, 2026
Search Tags:#voice generation#script transformation#delivery style#duration customization#AI script analysis
One-click install
npx skills add https://github.com/gooseworks-ai/gooseworks-ads-skills --skill format-script-to-style
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: format-script-to-style
Source: https://github.com/gooseworks-ai/gooseworks-ads-skills/tree/main/skills/atoms/voiceover/format-script-to-style
Command: npx skills add https://github.com/gooseworks-ai/gooseworks-ads-skills --skill format-script-to-style

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the challenge of converting an unformatted script into a voice script that matches a specific delivery style and duration, facilitating voice generation with a desired pacing and vibe.

Core Features & Use Cases

  • Script Transformation: Convert unformatted scripts into v3-tagged scripts ready for voice generation.
  • Style Matching: Match the script to a specific delivery style from a predefined set.
  • Duration Customization: Allow customization of the final spoken length of the script.
  • Use Case: Ideal for scenarios where an AI agent needs to apply a particular creative style and pacing to a script for voice generation.

Quick Start

To transform a script, use the following command: format-script-to-style delivery_style_name=style1 target_duration_seconds=60

Frequently Asked Questions about format-script-to-style

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I format a plain script for AI voice generation with a specific delivery style?▼

To format an unformatted script for voice generation, you transform it into a v3-tagged voice script by specifying a predefined delivery style and target duration. This applies the desired pacing and vibe to the text.

Can I set a target spoken duration when converting text into a v3-tagged voice script?▼

Yes, you can customize the final spoken length by providing a target duration in seconds. The script transformation adjusts the pacing to match the specified delivery duration.

What is a v3-tagged voice script and when do I need it?▼

A v3-tagged voice script is a formatted text output optimized for AI voice generation, containing specific tags for pacing and delivery style. You need it when applying a particular creative vibe to spoken audio.

How do I pass delivery style and duration parameters to transform my script?▼

You transform your script by using the command syntax with parameters for the style name and target duration in seconds. The system utilizes predefined style and duration data to generate the output.

Does the script transformation tool require the text to be uploaded as a file?▼

No, the tool requires access to the script content within the calling AI agent's conversation context. It processes in-context unformatted scripts directly from the active session.

What are the limitations when matching a script to a predefined delivery style?▼

The main limitation is that delivery styles must be selected from a predefined set available in the system. Additionally, the unformatted script must already exist in the calling agent's context.

Related Skills

Explore More Content & Communication Skills→
beshkenadzebeshkenadze
3

meeting-notes

Convert meeting transcripts into structured notes with decisions and action items.

Community
Basic
fishyerfishyer
1

TTS

Convert written text into spoken audio using the z-ai-web-dev-sdk.

Community
Intermediate
huiferhuifer
23

jd-analyzer

Extract structured skills, qualifications, and responsibilities from JD text into a predefined schema.

Community
Intermediate
wixettewixette
10

sag

Generate spoken audio from text using ElevenLabs TTS models.

Community
Intermediate