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 fileoutput_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
| Model |
Parameters |
Speed |
Accuracy |
Memory |
| tiny |
39M |
~32x |
Good |
~1GB |
| base |
74M |
~16x |
Better |
~1GB |
| small |
244M |
~6x |
Great |
~2GB |
| medium |
769M |
~2x |
Excellent |
~5GB |
| large |
1.5B |
1x |
Best |
~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
1---2name: whisper3description: Transcribe audio files to text using OpenAI Whisper4---56# Whisper Audio Transcription Skill78Transcribe audio files to text using OpenAI Whisper.910## Capabilities1112- Transcribe audio files (MP3, WAV, M4A, FLAC, OGG, etc.) to text13- Support for 90+ languages with auto-detection14- Optional timestamp generation15- Multiple model sizes (tiny/base/small/medium/large)16- Output in plain text or JSON format1718## Usage1920### Basic Transcription2122```bash23python3 scripts/transcribe.py <audio_file> <output_file>24```2526### With Options2728```bash29# Specify model size (default: base)30python3 scripts/transcribe.py audio.mp3 transcript.txt --model medium3132# Specify language (improves accuracy)33python3 scripts/transcribe.py audio.mp3 transcript.txt --language zh3435# Include timestamps36python3 scripts/transcribe.py audio.mp3 transcript.txt --timestamps3738# JSON output with metadata39python3 scripts/transcribe.py audio.mp3 output.json --format json40```4142## Parameters4344- `audio_file` (required): Path to input audio file45- `output_file` (required): Path to output text/JSON file46- `--model`: Whisper model size (tiny/base/small/medium/large, default: base)47- `--language`: Language code (e.g., en, zh, es, fr, auto for detection)48- `--timestamps`: Include word-level timestamps in output49- `--format`: Output format (text/json, default: text)5051## Model Sizes5253| Model | Parameters | Speed | Accuracy | Memory |54|--------|------------|-------|----------|--------|55| tiny | 39M | ~32x | Good | ~1GB |56| base | 74M | ~16x | Better | ~1GB |57| small | 244M | ~6x | Great | ~2GB |58| medium | 769M | ~2x | Excellent| ~5GB |59| large | 1.5B | 1x | Best | ~10GB |6061## Supported Audio Formats6263MP3, WAV, M4A, FLAC, OGG, AAC, WMA, and more (via FFmpeg)6465## Dependencies6667- Python 3.8+68- openai-whisper69- ffmpeg7071## Installation7273```bash74pip install openai-whisper75sudo apt-get install ffmpeg # Ubuntu/Debian76```
trpc-group