split-audio-by-words

Official

Split long-form audio files into per-scene mp3s with clean word boundaries.

Authorgooseworks-ai
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill addresses the challenge of cleanly splitting long-form audio files, such as podcasts, into per-scene mp3s, ensuring that cuts land on word boundaries rather than mid-syllables.

Core Features & Use Cases

  • Word-level Timestamps: Utilizes Whisper word-level timestamps to ensure precise scene breaks.
  • Explicit Scene Markers or Auto-Split: Offers the option to use explicit timestamps or automatically detect scene breaks based on long pauses.
  • Output Manifest: Generates a manifest.json file mapping scenes to source timestamps and caption text.
  • Use Case: For creating voiceover files for each scene in a podcast, allowing for accurate syncing with visuals.

Quick Start

Split the audio file 'podcast-episode.m4a' into scenes using Whisper word timestamps.

Dependency Matrix

Required Modules

whisperffmpeg

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: split-audio-by-words
Download link: https://github.com/gooseworks-ai/gooseworks-ads-skills/archive/main.zip#split-audio-by-words

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.