返回 Skill 列表
extension
分类: 内容与媒体无需 API Key

audio-extractor

从视频文件中提取音频到WAV格式。当您需要分析视频中的音频、准备用于能量计算的音频,或将视频音频转换为标准格式进行处理时使用。

person作者: jakexiaohubgithub

Audio Extractor

Extracts audio from video files to WAV format for further analysis. Converts to mono 16kHz PCM format optimized for speech/energy analysis.

Use Cases

  • Extracting audio for speech analysis
  • Preparing audio for energy calculation
  • Converting video audio to standard format

Usage

python3 /root/.claude/skills/audio-extractor/scripts/extract_audio.py \
    --video /path/to/video.mp4 \
    --output /path/to/audio.wav

Parameters

  • --video: Path to input video file
  • --output: Path to output WAV file
  • --sample-rate: Audio sample rate in Hz (default: 16000)
  • --duration: Optional duration limit in seconds (default: full video)

Output Format

  • Format: WAV (PCM 16-bit signed)
  • Channels: Mono
  • Sample rate: 16000 Hz (default)

Dependencies

  • ffmpeg

Example

# Extract first 10 minutes of audio
python3 /root/.claude/skills/audio-extractor/scripts/extract_audio.py \
    --video lecture.mp4 \
    --duration 600 \
    --output audio.wav

Notes

  • Output is always mono for consistent analysis
  • 16kHz sample rate is sufficient for speech analysis and reduces file size
  • Supports any video format that ffmpeg can read