[verdict][curated prompt][source: audiofetcher.com]
Can I vibecode AudioFetcher?
// buildable in a weekend, but real gaps stay open
The core loop is genuinely one-shottable: a small local UI, yt-dlp for the fetch, ffmpeg for the encode, files land in a folder. What is not a one sitting is everything that makes a public converter feel reliable week after week · YouTube bot checks, cookies/PO tokens, geo blocks, fair queues, abuse protection, and a hosted path so non-technical people never open a terminal. Build the personal script; do not expect one prompt to replace a maintained public service.
confidence: high
what it is: Paste a YouTube or playlist link, convert to MP3, and download · Pro adds 320 kbps and priority queue
Buildability index · an editorial game
- Price 6 $/month weight: plus 1
- Time one sitting weight: plus 3
- Category audio and video no weight
- Moat execution quality weight: minus 1
- Confidence high weight: plus 1
- What you lose 5 items weight: minus 2
- Site audiofetcher.com (si apre in una nuova scheda) no weight
The maths works, but not by much: look at what you lose before you start.
Gioco editoriale: il verdetto dice se un agente può, l’indice se conviene.
What you build
Accept a YouTube URL or playlist, download audio with yt-dlp, encode MP3 with ffmpeg, and save the file locally.
what you need
- Python or Node
- yt-dlp
- ffmpeg
- optional cookies or residential proxy if YouTube blocks datacenter IPs
Submitted by the maker. Honest split: personal CLI is a yes; public hosted converter with Pro queue is the kinda.
The prompt
A weekend with a coding agent. The gaps that stay are right below, under “what you lose”.
Build me a personal YouTube-to-MP3 tool to replace AudioFetcher for one user on my laptop. Requirements:
- Python 3.11 + a tiny localhost Flask or Starlette app; one page with a URL field,
quality select (128 / 192 / 256 / 320 kbps), and a Convert button.
- On submit, shell out to yt-dlp to pull best audio only, then ffmpeg to CBR MP3 at the
chosen bitrate. Write files into ./downloads with a safe title filename.
- Support a single video URL and a playlist URL. For playlists, show a checkbox list of
titles first (yt-dlp --flat-playlist --print), then convert only checked items one by one
with a simple progress log on the page (SSE or polling).
- Put YT_COOKIES_FILE and optional HTTP_PROXY in .env; pass them to yt-dlp when set.
If yt-dlp returns LOGIN_REQUIRED or bot-check text, show that error plainly and tell me
to export cookies from a logged-in browser.
- Cap each job at 3 hours of media; reject live streams. No accounts, no cloud, no queue
service for other users · this is just me.
- Out of scope: multi-tenant fair queues, Stripe/Pro billing, magic-link auth, public
abuse protection, mobile apps.
- README: install yt-dlp + ffmpeg, how to export Netscape cookies, and a blunt note that
YouTube blocks many datacenter IPs so a home machine or cookies may be required.Curated prompt: written and reviewed by hand for this app. In English on purpose — it is the language coding agents work best in.
What you lose
- hosted UI for non-technical users
- playlist preview with per-track checkboxes
- priority queue and 320 kbps Pro path
- someone else fighting YouTube bot checks, PO tokens, and geo blocks
- email magic-link Pro auth and fair multi-user queueing
Why people still pay
Power users already run yt-dlp. Everyone else pays to paste a link in a browser and get an MP3 without installing tools or debugging LOGIN_REQUIRED. The money is convenience plus the permanent maintenance of staying ahead of YouTube client checks, not a novel audio algorithm.
moat: Execution quality what a moat is
YouTube anti-bot upkeep / hosted convenience
Free alternatives
Not in the mood to build it? These already exist, they are free or open source, and we checked them one by one.
Rejected (2) — and why
- cobalt (si apre in una nuova scheda) — Lovely one-link downloader; AudioFetcher’s playlist job is still an open feature request.
- Seal (si apre in una nuova scheda) — Twenty-eight thousand stars, but the 2026 commits are monthly sponsor-copy edits; the last real code landed April 2025.
Who has already built it
Starting from here is still vibecoding: the prompt is for when you want it exactly your way.
- yt-dlp (opens in a new tab) — The actual download engine almost every converter wraps. Best DIY path is using it directly. (alive)
- cobalt (opens in a new tab) — Open-source multi-service media downloader with a self-hostable API and web UI. (alive)
- youtube-dl (opens in a new tab) — Older predecessor; still useful context for how long this cat-and-mouse has run. (alive)
Do you agree?
The vote balance
Ancora nessun voto: il tuo è il primo.
Nessun voto ancora — il primo pesa.
