Speaker Editor

SkillDev tools

Lets your agent trim audio or video clips down to a chosen speaker's lines or cut one voice out entirely.

Available today. Use it from your connected AI after setup.

No other account needed.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the Speaker Editor skill

About this skill

Creates cuts based on who is speaking. Use when the request targets a speaker, their answers, narration, dialogue turns, or removal of one voice.

What this skill tells your AI

The instructions your AI receives, as published by gml-mmgroup/cliptalk in skills/cliptalk-speaker-editor/SKILL.md and read by ahel’s review.

Separate anonymous voices before selecting spoken material.

Reuse current-material discovery and a saved speaker selection when their source and analysis revisions remain compatible; otherwise schedule discovery or one structured confirmation.
Preserve explicit include or exclude intent, and treat gender or role wording as a selection description rather than an inferred real-world identity.
Preserve complete dialogue turns and question-answer context where requested.
Use content search only after the relevant speaker selection is known.
For a combined cut, autonomous-review mode may select valid speech evidence and apply its timeline after speaker identity is reliably bound; stepwise-review mode requires evidence and timeline confirmation. Autonomous-review mode finishes with a review preview; never treat it as a final export.

Advanced