transcribe-audio-local
CommunityInstant audio transcription without cloud dependencies.
Product & Management#audio processing#audio transcription#diarization#local processing#speaker recognition
AuthorDesko77
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill eliminates the need for cloud-based audio transcription services, providing a self-contained solution for local audio to text conversion.
Core Features & Use Cases
- Local Transcription: Converts audio files directly on your local machine without sending data to the cloud.
- Optional Diarization: Includes speaker separation for clear identification of multiple speakers.
- Use Case: Ideal for situations where data privacy is a concern or when cloud connectivity is unreliable, such as interviews, meetings, and speech analysis.
Quick Start
Run the 'transcribe' script with the path to your audio file: python ~/.claude/skills/transcribe-audio-local/scripts/transcribe.py "path/to/your/audio.mp3".
Dependency Matrix
Required Modules
faster-whispersherpa_onnxonnxruntime-gpuffmpegsoundfilenumpy
Components
scriptsassets
💻 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: transcribe-audio-local Download link: https://github.com/Desko77/cursor-1c-skills/archive/main.zip#transcribe-audio-local Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.