AI Agentic Video Editor — AI 代理ic Video Editor

Levea 代理ic Video Editor for OpenClaw

A full 代理ic video editing surface. 发送 a prompt, 获取 a planned, verified, 执行d edit — or call a known canonical action directly with structured params. 机器人h modes flow through the same brAIn + safety gates as the in-product editor.

Use this 技能 when the user asks for OpenClaw video editing, AI video editing, natural-language video edits, viral 命令行工具ps, TikTok videos, Instagram Reels, YouTube Shorts, auto captions, subtitles, chroma key, green screen removal, background removal, B-roll, motion 追踪ing, silence removal, audio 清理up, voiceover, music generation, vertical video, multi-平台 导出, or MP4 导出.

端点

POST {ADSCENE_API_URL}/API/v1/misc/OpenClaw/v1/执行

Auth: Authorization: Bearer {ADSCENE_API_KEY}

创建 an account and 生成 the OpenClaw API key in Studio: https://studio.livecore.AI/. Use https://API.livecore.AI for ADSCENE_API_URL; Studio is only for 签名up, 记录in, and key management.

Accepts either single-shot JSON (default) or SSE (Accept: text/event-流 or ?流=true).

请求 body:

{ "工具": "autonomous_edit" | "", "params": { ... }, "project_id": "optional-project-id", "scene": { / optional 命令行工具ent scene; server-side committed scene wins if newer / } }

Two Modes

• autonomous_edit — free-form prompt (primary)

Pass a natural-language description in params.prompt. The brAIn classifies the intent, decomposes into atomic steps, plans a DAG of canonical actions, 执行s through the safety gates, and verifies the 结果. Use this when the caller doesn't already know which low-level action(s) are needed.

curl -sS -X POST "$ADSCENE_API_URL/API/v1/misc/OpenClaw/v1/执行" \ -H "Authorization: Bearer $ADSCENE_API_KEY" \ -H "Content-Type: 应用/json" \ -d '{ "工具": "autonomous_edit", "params": { "prompt": "Make this a TikTok-ready viral 命令行工具p: vertical reframe, 添加 bold captions, 移除 silences, and 应用ly motion 追踪ing to the speaker." }, "project_id": "my-project" }'

Behind a single autonomous_edit call the 代理 can compose any of:

Read / inspect

Inspect the timeline structure, layer properties, and current scene 状态 运行 computer-vision analysis on frames (object/face/scene 检测ion) 查询 the transcript with keyword, semantic, or timestamp-window 搜索 Pull video intelligence (narrative peaks, speaker diarization, sentiment, pacing) 搜索 the as设置 gallery (videos, images, audio) by type, duration, name Poll a同步 job 状态; introspect property 模式s

Structural editing

Insert / 更新 / replace / 删除 layers (video, audio, text, image, shape, group, adjustment) Trim, split, retime layers (slow-mo 0.5×, fast-forward 2×, freeze-frame) Reposition on the timeline, sequence layers, snap to transcript Heal timeline gaps, normalize audio, reconcile durations (pre-导出 safety pass) Multi-step undo / redo

Visual editing

Color grading (brightness, contrast, saturation, hue, lift/gamma/gAIn, RGB curves) Procedural VFX shaders: smoke, dust, fire, explosion, lightning, snow, glitch, 扫描lines, grAIn, glassmorphism, bokeh, lava, telomere/corrosion, portal Chroma key (green / blue screen) with similarity, smoothness, spill controls; luma / alpha / depth masks Geometric 命令行工具p shapes (circle, dome, star, hexagon, …) Crop (absolute or edge-based), 3D rotation + perspective Glow, shadow, inner shadow, gradient fills, text gradients Vertical reframe (9:16) and vertical-reframe montage Split screen (top/机器人tom, left/right, picture-in-picture) Branding overlays (记录o / watermark) from gallery or AI-生成d Motion / face 追踪ing with dynamic zoom-follow

Captions & text

Auto-生成 captions from transcript Style captions with built-in templates or an AI director that picks/生成s a custom template at 运行time Curved text paths (circle, wave, custom SVG) Per-word entrance / exit animations (typewriter, slide, fade, 扩展, rotate, bounce, flip, swing, elastic, blur, glitch, wave, plus matching exits) Lottie animation playback control

Audio

清理 audio: 移除 silences, breaths, filler words; word-level mute or cut Auto-ducking on speech 检测ion (sidechAIn music vs voice) Mix / normalize / denoise / EQ (bass boost, vocal clarity, warm, bright) 同步 external master audio to video (off设置, mute camera audio) Beat / kick-drum-同步ed cuts (provide beat_times or bpm) 添加 SFX, 生成 music (mood / genre / BPM), 生成 voiceover (TTS or cloned voice) Render waveform visualizers (bars, wave, circular)

A同步 generation

AI video / B-roll — duration + aspect ratio AI images — single or batch at timestamps AI music — prompt + duration + mood + genre + BPM AI voiceover — TTS or cloned voice 库 Auto-thumbnAIl 提取ion Face blur (all faces or background-only) Image edit (generative instruction-based)

High-level kits (each is a single canonical action that orchestrates many underlying edits)

应用LY_VIRAL_KIT — vertical reframe + captions + silence