mcpField
W
whisper-transcription

whisper-transcription

github.com/guia-matthieuCreative & media150948 installsUpdated 4w ago
Repository

About whisper-transcription

Whisper Transcription is a skill and command-line workflow for turning audio and video into text with OpenAI's Whisper. It is intended for people processing recordings into transcripts, subtitles, translated text, or timestamp data.

Key features

  1. 01Transcribe audio and video files
  2. 02Batch-process recordings in a folder
  3. 03Export TXT, SRT, VTT, JSON, or TSV
  4. 04Translate transcription into a target language
  5. 05Extract timestamps in JSON format
  6. 06Choose a Whisper model

Use cases

  1. 01Create subtitles for a video
  2. 02Convert podcast episodes into transcripts
  3. 03Process a folder of interview recordings
  4. 04Translate foreign-language audio into English

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/guia-matthieu/clawfu-skills --skill whisper-transcription

After installing, type/whisper-transcriptionin Claude Code to confirm it loaded.

Bundled filesscripts/main.pyscripts/requirements.txt

Details

From the project README

Whisper Transcription

Transcribe any audio or video to text using OpenAI's Whisper model - the same technology powering ChatGPT voice features.

When to Use This Skill

  • Podcast repurposing - Convert episodes to blog posts, show notes, social snippets
  • Video subtitles - Generate SRT/VTT files for YouTube, social media
  • Interview extraction - Pull quotes and insights from recorded calls
  • Content audit - Make audio/video libraries searchable
  • Translation - Transcribe and translate foreign language content

What Claude Does vs What You Decide

Claude DoesYou Decide
Structures production workflowFinal creative direction
Suggests technical approachesEquipment and tool choices
Creates templates and checklistsQuality standards
Identifies best practicesBrand/voice decisions
Generates script outlinesFinal script approval

Dependencies

pip install openai-whisper torch ffmpeg-python click
# Also requires ffmpeg installed on system
# macOS: brew install ffmpeg
# Ubuntu: sudo apt install ffmpeg

Commands

Transcribe Single File
python scripts/main.py transcribe audio.mp3 --model medium --output transcript.txt
python scripts/main.py transcribe video.mp4 --format srt --output subtitles.srt
Batch Transcription
python scripts/main.py batch ./recordings/ --format txt --output ./transcripts/
Transcribe + Translate
python scripts/main.py translate foreign-audio.mp3 --to en
Extract Timestamps
python scripts/main.py timestamps podcast.mp3 --format json

Examples

Example 1: Podcast to Blog Post
# Transcribe 1-hour podcast
python scripts/main.py transcribe episode-42.mp3 --model medium

# Output: episode-42.txt (full transcript with timestamps)
# Processing time: ~5 min for 1 hour audio on M1 Mac
Example 2: YouTube Subtitles
# Generate SRT for video upload
python scripts/main.py transcribe marketing-video.mp4 --format srt

# Output: marketing-video.srt
# Upload directly to YouTube/Vimeo
Example 3: Batch Process Interview Library
# Transcribe all recordings in folder
python scripts/main.py batch ./customer-interviews/ --model small --format txt

# Output: ./customer-interviews/*.txt (one per audio file)

Model Selection Guide

ModelSpeedAccuracyVRAMBest For
tinyFastest~70%1GBQuick drafts, short clips
baseFast~80%1GBSocial media clips
smallMedium~85%2GBPodcasts, interviews
mediumSlow~90%5GBProfessional transcripts
largeSlowest~95%10GBCritical accuracy needs

Recommendation: Start with small for most marketing content. Use medium for client deliverables.

Output Formats

FormatExtensionUse Case
txt.txtBlog posts, analysis
srt.srtVideo subtitles (YouTube)
vtt.vttWeb video subtitles
json.jsonProgrammatic access
tsv.tsvSpreadsheet analysis

Performance Tips

  1. GPU acceleration - 10x faster with CUDA GPU
  2. Audio extraction - Script auto-extracts audio from video
  3. Chunking - Long files auto-split for memory efficiency
  4. Language detection - Automatic, or specify with --language

Skill Boundaries

What This Skill Does Well
  • Structuring audio production workflows
  • Providing technical guidance
  • Creating quality checklists
  • Suggesting creative approaches
What This Skill Cannot Do
  • Replace audio engineering expertise
  • Make subjective creative decisions
  • Access or edit audio files directly
  • Guarantee commercial success

Related Skills

Skill Metadata

  • Mode: cyborg
category: automation
subcategory: audio-processing
dependencies: [openai-whisper, torch, ffmpeg-python]
difficulty: beginner
time_saved: 10+ hours/week

Comments

Markdown supported