Audio preprocessing and transcription pipeline using ffmpeg + OpenAI Whisper. Use this skill whenever the user wants to transcribe audio or video files (lectures, meetings, podcasts, interviews), improve audio quality before transcription, remove silence from recordings, or mentions Whisper, speech-to-text, or transcricao. Also trigger when the user has MKV, MP4, WAV, M4A, or other media files they want converted to text. This skill handles the full pipeline: audio extraction, silence removal, voice enhancement, segmentation, and Whisper transcription. Works 100% offline.
$npx -y skills add j0ruge/skills_commands_manager --skill whisper-preprocessInstalls into the current project.
Run `npx skills use "https://github.com/j0ruge/skills_commands_manager" --skill "j0ruge/skills_commands_manager/whisper-preprocess"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/j0ruge/skills_commands_manager" that are relevant to the current task. Run `npx skills add "https://github.com/j0ruge/skills_commands_manager"` and select the relevant skills, then follow their instructions.