vocateca
Podcasts, YouTube & Instagram → on-device transcription → searchable Markdown library.
Everything runs on your Mac. No cloud APIs, no telemetry, no account required to transcribe.
Native SwiftUI · WhisperKit · Apple Silicon.
What it does
🎧 Podcasts
Find feeds by name (Apple Podcasts/iTunes directory) or paste any RSS URL. Resumable downloads, automatic daily checks.
📺 YouTube
Subscribe to channels by any URL form. Captions-first (manual tracks only); WhisperKit fallback when none available.
Reels, posts, and stories from accounts you follow — using your own login, via gallery-dl. No third-party API.
📥 Local files & URLs
Drop audio/video files, import a folder, or paste any URL yt-dlp recognises (SoundCloud, Vimeo, and hundreds more).
🔒 Fully on-device
WhisperKit runs on Apple Silicon GPU via CoreML/Metal. Audio and transcripts never leave your Mac.
📝 Obsidian-ready library
One .md per episode with YAML frontmatter, plus optional .srt for timestamped quotes. Drop the folder into any Obsidian vault.
Free vs. vocateca Pro
The guiding rule: active click = free, runs without you = Pro. Everything you trigger manually is free forever. Pro (€4.90/month or €49/year, incl. VAT — about the price of a coffee; cancel anytime) adds the automation layer.
| Feature | Free | Pro |
|---|---|---|
| Add & browse all sources (Podcasts, YouTube, Instagram) | ✅ | ✅ |
| Manual download + transcription | ✅ | ✅ |
| Searchable Markdown library + .srt export | ✅ | ✅ |
| Scheduler — automatic daily source checks | — | ✅ |
| Folder watch — auto-ingest dropped files | — | ✅ |
| Background daemon — transcribes with the window closed | — | ✅ |
Privacy
WhisperKit runs entirely on-device using CoreML and Metal — no OpenAI API key, no cloud inference.
Your audio and transcripts stay on your Mac (in the output folder you choose and in
~/Library/Application Support/Vocateca/).
Telemetry requires explicit opt-in. Instagram login is handled by gallery-dl via a session
cookie stored in your macOS Keychain — nothing is sent anywhere except Instagram's own servers.
Open source
vocateca is MIT licensed. It builds on: WhisperKit (MIT), GRDB.swift (MIT), FeedKit (MIT), Yams (MIT), ffmpeg (LGPL), yt-dlp (Unlicense), gallery-dl (GPL-2.0).