vivadicta transcribe flow

Use this skill to turn an audio file or a YouTube URL into a searchable transcription in the user's VivaDicta history. Covers input-shape detection, blocking vs --async, progress output, and recovery paths.

Preconditions

• VivaDicta.app installed at /Applications/VivaDicta.app and running (writes require the UI).
• User has a transcription model configured (Whisper local, Parakeet local, or a cloud provider with API key in Keychain).
• For YouTube URLs, the app's YouTube transcription is enabled (one of: captions → Apify → yt-dlp → Whisper).

Pick the source and invocation

# Local file, blocking (default) - waits until done, prints the final transcription summary
vivadicta transcribe ~/Downloads/meeting.m4a

# YouTube URL, blocking
vivadicta transcribe "https://youtu.be/dQw4w9WgXcQ"