domains / families / media / ra-local-talking-head-cut

ra-local-talking-head-cut

separate

Produce a polished local talking-head or narrated screen-recording rough cut without a cloud editor. Use when Codex must clean Chinese or mixed Chinese-English speech, correct product terminology before semantic editing, compress pauses without making speech breathless, preserve source resolution and frame rate, normalize dialogue loudness, generate final-audio subtitle artifacts, or benchmark local output against ChatCut/video-use/chengfeng/AI剪口播.

When to use

• clean Chinese or mixed Chinese-English speech
• correct product terminology before semantic editing
• compress pauses without making speech breathless
• preserve source resolution and frame rate
• normalize dialogue loudness
• generate final-audio subtitle artifacts
• benchmark local output against ChatCut/video-use/chengfeng/AI剪口播

When not to use

• cloud editing
• guessing uncertain model or product names
• building an EDL or rendering a cut while approval is pending
• blanket deletion of every pause above 200 ms
• adding blanket transitions
• reusing precut-review.srt after timeline edits

Skill page

Source