whisper-beat-finder

Community

Turn audio into beat-timed transcripts

AuthorRinDig
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Convert spoken audio into a beat-timed transcript by leveraging Whisper word timestamps.

Core Features & Use Cases

  • Transcribes audio to a word-timestamped transcript (transcript.json) using Whisper.
  • Derives beat boundaries by matching distinctive phrases from a script to the transcript.
  • Outputs beat timings (beat-timings.md) with absolute start times and optional sub-callouts for animation cues.
  • Provides CPU-safe defaults and GPU fallback guidance to balance reliability and performance in production.

Quick Start

Place the mp3 in the project and run the transcribe.py script followed by the beat-finder to generate transcript.json and beat-timings.md.

Dependency Matrix

Required Modules

openai-whisper

Components

scripts

💻 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: whisper-beat-finder
Download link: https://github.com/RinDig/Interpreted-Context-Methdology/archive/main.zip#whisper-beat-finder

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 510,000+ vetted skills library on demand.