Video Voice Changer is an automated audio-video processing skill for Claude Code that extracts video soundtracks, alters vocal characteristics using distinct voice presets, and seamlessly merges the altered audio back into the original container. Powered by FFmpeg and Python, it supports multiple voice types including male, female, robotic, and child presets. The skill ensures lossless video quality retention by only modifying the audio stream, while safely outputting new files by default to avoid overwriting source media.
主要功能
01Automated audio extraction, voice transformation, and video remuxing
02Automatic cleanup of intermediate audio processing files
03Lossless video quality preservation by modifying only audio streams
04615 GitHub stars
05Pre-configured vocal presets including female, deep male, child, and robot voices
06Safe non-destructive file creation by default with optional overwrite mode
使用场景
01Automating creative pitch and timbre shifts in tutorial and presentation videos
02Anonymizing voices or disguising speaker identities in video recordings
03Creating distinct character voiceovers for social media, animations, or gaming content