01 / PLAN
Start with the result and the source
TTS text may include phonetic spellings that sound correct but look wrong on screen. Keep a clean display script and use it to correct the automatic transcript without losing the speech-derived timing.
Write for listening rather than silent reading. Short sentences, deliberate punctuation, and a quick pronunciation test usually improve a voiceover more than an extreme speed adjustment.
02 / WORKFLOW
Complete the workflow step by step
- Prepare.
Finish the TTS audio edit and place every narration section at its final PeteCut timeline position.
- Set up.
Run Auto captions using the timeline source and choose the spoken language.
- Create.
Compare generated captions with the clean display script, correcting names, punctuation, numbers, and phonetic substitutions.
- Review.
Split dense lines, protect safe areas, and watch the full project muted before export.
03 / QUALITY CHECK
Review the result before the next step
Listen from beginning to end with headphones. Check names, numbers, pauses, volume, and whether the delivery still communicates the intended meaning.
- Captions begin with the spoken phrase.
- Display text uses normal spelling.
- Lines are short enough to scan.
- Text stays readable on the target screen.
04 / QUESTIONS
Common question
Why transcribe text that already exists?
Transcription aligns caption segments with the audio as it is actually placed and spoken on the timeline; the script is then useful for correcting the words.
Can I update this workflow later?
Yes. Save the source and project details, then update the relevant settings, content, or output when the destination requirements change.