Text To Speech

Masters synthesized voiceover with FFmpeg: artifact cleanup, -23 LUFS loudnorm, atempo or silence pad, boundary fades, and segment stitch for video. Use for TTS, LUFS, or voiceover export. Do not use for Whisper transcripts (automatic-speech-recognition) and not a live-mic capture chair.

Kayforkind Updated 0 repo stars

File contents

Kayforkind/skill-slice commit 0f3769a140

Frequently asked questions

npx get-skill add kayforkind/text-to-speech