MaxiMind
Hub My tools API Guide checking…

Big-model Whisper transcription

Drop one or many audio / video files, then click Process. They run one at a time.

Design Studio Sign-in codes AI Tasks AI Limits
not tested
Works on your local network & Tailscale. On the public link, sign in with Google instead.
These apply to files dropped from now on. Change them anytime for new files.
Drop files here
…or click to choose. Drop many at once — they wait until you click Process. Small videos: audio is extracted in-browser; big videos upload as-is on LAN/Tailscale (server extracts).
Record from microphone
Transcribe from URL (YouTube, TikTok, etc.)
Retrieves existing YouTube captions directly, or downloads the audio to transcribe if not available.
Queue (0)
No files yet — drop one above, then click Process.
Loading channels from all your Buffer accounts…

Official Skills

Loading approved skills…