Module F / Guide / 10-20 min
Custom vocabulary: stop the AI from mishearing your jargon
Feed names, protocols, tickers, product words, and community terms into transcription review.
TL;DR
Use this lesson to feed names, protocols, tickers, product words, and community terms into transcription review. Treat it as practical guidance, not a rigid rulebook.
Why it matters
Captions make clips understandable without sound, searchable after publishing, and reviewable by editors before export. The goal is to help you make a stronger clip without taking away your creative freedom.
What you will learn
Prerequisites
- An audio file, video file, URL, or exported clip
- A target output format such as SRT, VTT, burned-in MP4, or transcript text
What you need
Core concept
Caption work is part accuracy and part design. The workflow only works if viewers can read the result quickly on a phone.
Example
Scenario
Auto-captions are mostly correct, but the clip contains names, numbers, jargon, or fast speech.
Move
Apply the workflow to a short section first and proofread the result at phone size.
Result
The caption pass becomes readable and accurate enough that sound-off viewers can follow the clip.
How to do it
- 1List names, tickers, protocols, product words, acronyms, slang, and community terms before transcription.
- 2Add phonetic notes or preferred spelling where the tool supports it.
- 3Run a short sample and check whether the vocabulary terms improve.
- 4Proof every vocabulary term manually because custom lists reduce errors but do not eliminate them.
- 5Keep the vocabulary list updated as new creators, products, and phrases appear.
Expected output
A caption or transcript artifact that is proofread, timed, readable on a phone, and matched to the target platform.
Practice task
Produce a clean caption pass
- 1Take a 20-30 second section of a real clip.
- 2Apply the caption or transcript workflow from this lesson.
- 3Proofread it with sound on, then watch it again with sound off at phone size.