media-audio-download

To extract audio from a Bilibili video for transcription, provide the video URL to download the audio track using yt-dlp. The output audio format is suitable for Speech-to-Text engines like Whisper.

No, downloading audio from Xiaohongshu notes requires Playwright instead of yt-dlp. The Skill uses Playwright to handle Xiaohongshu sources and extract the spoken audio content for transcription.

Yes, ffmpeg is required for audio extraction from video links. It processes the downloaded media into audio file formats ready for Speech-to-Text transcription workflows.

CookieCloud authentication provides the necessary credentials to access restricted video sources for audio extraction. It allows the Skill to securely download audio tracks from Bilibili and Xiaohongshu platforms.

The best way to prepare video content for Whisper is extracting the audio track into a compatible format. This Skill downloads and processes the audio using yt-dlp and ffmpeg, outputting files ready for STT engines.

Limitations include relying on external dependencies like yt-dlp, Playwright, and ffmpeg, which must be installed. Additionally, accessing restricted content requires setting up CookieCloud authentication beforehand.