ClipTalk — An AI agent that edits videos through conversation. Just say it, it's edited. ClipTalk — An AI agent that edits videos through conversation. Just say it, it's edited.
Produces evidence-backed cover candidates and reviewable cover variants for a ClipTalk video. Use when the user asks for a cover, poster frame, thumbnail, or multiple cover directions; do not use for timeline editing or social-video reframing.
Creates a subject-aware, time-varying crop track and a review-only social-format preview from an accepted ClipTalk cut. Use for automatic vertical, square, or portrait reframing; do not use for a fixed manual crop or before content editing is accepted.
Produces a task-local audio-polished preview or output from an existing cut, applying loudness normalization, optional noise reduction, fades, muting, and voice-first mix policy.
Adds relevant B-roll or cutaway overlays to an existing timeline while preserving the primary audio and making the result reviewable before final export.
Lays out subtitles for an existing ClipTalk timeline, including top/bottom placement, safe margins, readable wrapping, bilingual order, and review rendering.
Locates and assembles source passages matching a semantic request. Use for extracting explanations, topics, quotes, demonstrations, or other specifically described content.
Creates task-local cover candidates and composes the confirmed cover into the beginning of the current output as a short intro, keeping cover selection separate from video editing.
Checks an existing ClipTalk render for delivery defects such as decode failures, duration or stream mismatch, black or frozen frames, long silence, and incorrect dialogue loudness. Use for final checks, export readiness, or diagnosing a suspicious rendered file; it does not edit the timeline.
Converts an existing cut or freshly generated review output to vertical, square, or horizontal formats using shot-aware safe-area checks and complete-frame blurred padding by default.
Adds task-local graphic text layers such as title cards, top labels, product tags, price or parameter callouts, watermarks, and CTA overlays to an existing timeline.
Finds and assembles the strongest moments from a source video. Use when the requested result is a highlight reel, recap, trailer, or best-moments cut rather than a literal content extraction.
Produces a coherent interview edit by combining speaker discovery, topic selection, dialogue context, cleanup, subtitles, and preview. Use for interviews, podcasts, testimonials, or question-and-answer recordings.
Export the current ClipTalk edit state as a local JSON draft package for external editor bridges such as Jianying or CapCut, without writing into third-party application directories.
Generate local motion-graphics clips such as title cards, animated intros, visual explainers, and cover motion using the built-in HTML/Playwright/FFmpeg pipeline without external APIs.
Builds balanced clips from multiple required topics or categories, such as one segment per appliance, speaker, product, feature, or scene type, and reports missing categories instead of filling with unrelated footage.
Creates cuts based on who appears on screen. Use when the user wants to keep, remove, follow, or compare visible people rather than select by spoken content alone.
Revises an existing ClipTalk cut or review timeline. Use when the user asks to shorten, reorder, remove, restore, subtitle, or otherwise refine an existing result without redoing source analysis unnecessarily.
Finds and assembles a reviewable short-form cut with a strong opening hook. Use for Shorts, Reels, social clips, talking-head cutdowns, or requests for a punchier opening.
Creates a review-only 9:16, 4:5, 1:1, or 16:9 version from an existing accepted ClipTalk cut, then checks the rendered preview. Use only when a cut already exists and the user asks to adapt it for Shorts, Reels, Douyin, Xiaohongshu, WeChat Channels, or square feeds; do not use when the user still needs content found…
Verifies that a ClipTalk Agent plan uses the current task, source revision, selected scope, and task-local artifacts before reusing analysis, covers, subtitles, timelines, or outputs.
Revises subtitles on an existing ClipTalk timeline with readable placement, timing, line wrapping, and style-safe review output. Use when the user asks to add, fix, move, restyle, or verify subtitles without redoing source analysis.
★not rated 109 todayA55 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: