// catalog · ls -la /lab/tools
Catalog/page 23/24
Showing entries 133 to 138 of 139 · click any row to launch
- 133 Vision / Audio audio-quotes:// Pulls the most quote-able lines from a transcript. The ones that work standalone, that someone would actually screenshot. Each comes with: the verbatim quote, speaker (if named), and a one-line "why this works as a quote".
- 134 Vision / Audio audio-language:// Detects the spoken language from any audio sample. Returns the primary language with confidence, the second-most-likely (helpful for code-switched audio), and a 5-10 second sample of "transcript-as-evidence". Whisper handles ~99 languages.
- 135 Vision / Audio audio-speakers:// Speaker diarisation: detects who spoke when. Returns a timeline of speaker turns + a roll-up of total speaking time per speaker (with %). For meeting analytics, podcast editing, interview transcripts.
- 136 Vision / Audio podcast-clips:// Suggests 5 standalone clip windows (~60 sec each) from a long-form audio transcript. Each clip has: timestamps, a transcript excerpt, a one-line "why this works", and a suggested social-post caption. For podcast / interview / talk highlight reels.
- 137 Vision / Audio voicenote-todo:// Turns a rambling voice memo into a clean todo list. Catches natural phrasings ("remind me to call John", "don't forget the dentist Tuesday", "I need to file the report"). Each todo gets a verb-first formatting, an inferred priority, and a date if mentioned.
- 138 Vision / Audio interview-notes:// Turns an interview transcript (job interview, customer research, journalism) into structured notes. Pulls out: questions asked, key responses (paraphrased + 1-2 verbatim quotes), themes across the conversation, follow-ups to chase. For post-interview synthesis.