mcpField
W
whisper

whisper

github.com/trpc-groupCreative & media1.9k50 installsUpdated today
Repository

About whisper

whisper is a skill for transcribing audio files with OpenAI Whisper, for people working with recorded audio. It supports varied audio formats, more than 90 languages, optional timestamps, and text or JSON output.

Key features

  1. 01Transcribe multiple audio formats
  2. 02Auto-detect 90+ languages
  3. 03Optionally generate timestamps
  4. 04Choose from multiple model sizes
  5. 05Output text or JSON

Use cases

  1. 01Turn recordings into text
  2. 02Add timestamps to a transcript
  3. 03Create transcripts in JSON format

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/trpc-group/trpc-agent-go --skill whisper

After installing, type/whisperin Claude Code to confirm it loaded.

Bundled filesscripts/transcribe.py

Details

From the project README

Whisper Audio Transcription Skill

Transcribe audio files to text using OpenAI Whisper.

Capabilities

  • Transcribe audio files (MP3, WAV, M4A, FLAC, OGG, etc.) to text
  • Support for 90+ languages with auto-detection
  • Optional timestamp generation
  • Multiple model sizes (tiny/base/small/medium/large)
  • Output in plain text or JSON format

Usage

Basic Transcription
python3 scripts/transcribe.py <audio_file> <output_file>
With Options
# Specify model size (default: base)
python3 scripts/transcribe.py audio.mp3 transcript.txt --model medium

# Specify language (improves accuracy)
python3 scripts/transcribe.py audio.mp3 transcript.txt --language zh

# Include timestamps
python3 scripts/transcribe.py audio.mp3 transcript.txt --timestamps

# JSON output with metadata
python3 scripts/transcribe.py audio.mp3 output.json --format json

Parameters

  • audio_file (required): Path to input audio file
  • output_file (required): Path to output text/JSON file
  • --model: Whisper model size (tiny/base/small/medium/large, default: base)
  • --language: Language code (e.g., en, zh, es, fr, auto for detection)
  • --timestamps: Include word-level timestamps in output
  • --format: Output format (text/json, default: text)

Model Sizes

ModelParametersSpeedAccuracyMemory
tiny39M~32xGood~1GB
base74M~16xBetter~1GB
small244M~6xGreat~2GB
medium769M~2xExcellent~5GB
large1.5B1xBest~10GB

Supported Audio Formats

MP3, WAV, M4A, FLAC, OGG, AAC, WMA, and more (via FFmpeg)

Dependencies

  • Python 3.8+
  • openai-whisper
  • ffmpeg

Installation

pip install openai-whisper
sudo apt-get install ffmpeg  # Ubuntu/Debian

Comments

Markdown supported