download_audio

Supports YouTube, Vimeo, TikTok, Twitter, SoundCloud, and 1000+ sites.

Speed Optimizations

aria2c multi-connection downloads (16 parallel connections)
Concurrent fragment downloading (4 fragments)
No video download, audio extraction only (up to 200x faster than downloading full video)
No format conversion, native audio format preserved

Example

Request:

{
  "url": "https://youtube.com/watch?v=xxx",
  "output_dir": "~/Downloads"
}

Response:

{
  "success": true,
  "url": "https://youtube.com/watch?v=xxx",
  "output_dir": "/Users/you/Downloads",
  "file": {
    "path": "/Users/you/Downloads/Video_Title_dQw4w9WgXcQ.webm",
    "filename": "Video_Title_dQw4w9WgXcQ.webm",
    "size_mb": 14.49
  },
  "aria2c_used": true,
  "message": "Audio downloaded to /Users/you/Downloads/Video_Title_dQw4w9WgXcQ.webm"
}

Parameters

Parameter	Required	Default	Description
`url`	Yes	—	Video URL to download audio from (YouTube, Vimeo, TikTok, etc.)
`output_dir`	No	`~/Downloads`	Directory to save the audio file

Notes

The downloaded file path is ready to pass directly to transcribe_audio or search_audio.

Audio format depends on the source. YouTube returns .webm, SoundCloud returns .m4a, etc. No conversion is done, keeping downloads fast.

Filenames are sanitized to ASCII characters only — spaces, smart quotes, and special characters are replaced with underscores. This prevents file path issues when passing downloads to other tools.

Core

Search

Analysis

Processing

Memory

download_audio

Speed Optimizations

Example

Parameters

Notes

​Speed Optimizations

​Example

​Parameters

​Notes

Speed Optimizations

Example

Parameters

Notes