ai-video-editor

Timeline Studio — Browser AI Video Editor

English | 中文 | 日本語 | 한국어 | Español | Français | Deutsch | Português | ไทย | Tiếng Việt | Русский

Responsible use of deep synthesis

This tool uses deep-synthesis technology and is intended solely for technical research and learning.

Users must ensure that they:

• use only facial images or videos of themselves or people who have provided lawful authorization;
• do not create or distribute any illegal, infringing, false, or misleading content;
• do not present generated content as authentic footage or impersonate another person without their consent.

Users are solely responsible for any legal liability arising from violations of these requirements.

Project updates

• 2026-09-17 — WebMCP finishing and review: 21 browser tools now cover 26 reviewed edits, including timed-clip movement and source trimming, overlay transforms, caption style/position and project framing. Agents can request rendered frame/audio samples, run browser-local voiceover or transcription with progress and cancellation, and review results before timeline insertion. New controls and messages support all 13 interface languages.
• 2026-09-15 — Edited audio export: exporting an audio clip now renders its trimmed range with playback speed, volume, fades and space effects applied. Clips and the complete timeline mix can be exported as WAV or MP3; audio-only export is available alongside video export.
• 2026-09-14 — Export reliability: clips with solid-color backgrounds and opacity keyframes now export correctly without a person mask. Failed exports keep the error visible and can be retried with the same settings.
• 2026-09-14 — Large-project performance: project import reduces main-thread work, while cached audio-lane calculations, compact waveform rendering and fewer audio seeks make scrubbing and playback lighter. Media, clip timing, editing controls, effects and export behavior are preserved. Import shows real progress and opens the editor once media is restored; thumbnails continue refining in the background.
• September 11, 2026 — WebMCP editing and video delivery: 15 browser tools now cover reviewed caption changes, audio volume and fades, markers, main-visual splitting/deletion/duplication, existing-asset discovery and insertion, and picture-in-picture. Agents can prepare export settings, start the real editor exporter, inspect progress and actual output metadata, or cancel. Multi-operation edits retain conflict checks, ripple behavior, track locks and undo; repeated export requests do not trigger duplicate downloads. Tool and review copy covers all 13 interface languages.

See the public Roadmap for planned work, Releases for shipped changes, and Issues for focused tasks and bugs.

What can it produce?

Explore reproducible before/after examples and editing recipes:

→ AI Video Editing Skills Handbook

Timeline Studio is a local-first AI video editor that runs in the browser. It combines a CapCut-style multi-track timeline with WebGPU AI music and repair, multilingual voiceovers, automatic captions, talking-avatar generation, and deterministic offline export.

Open the editor · Watch on YouTube · Hugging Face Space

Video demo

Auto Edit

Visual analysis, keyframes, captions, and export.

https://github.com/user-attachments/assets/e8327caa-429e-40ff-a7fe-a59e6cf7a464

AI Repair

Timed watermark removal with before/after review.

https://github.com/user-attachments/assets/aea9f5b4-c720-4b0c-9067-5ec124eef982

AI Voiceover

https://github.com/user-attachments/assets/304a744e-d620-4380-9c17-19af3726f5a4

AI capabilities

• Multilingual voiceover: Chinese and mixed Chinese/English Hojo TTS Light 80M FP16 reference voices (晴岚 and 若溪), with autoregressive generation on WebGPU and stable waveform decoding on WASM; English Kokoro 82M; and browser Piper voices for German, Spanish, French, Italian, and Brazilian Portuguese.
• Local AI music: Stable Audio 3 Small Q4 ONNX runs through WebGPU with translated free-form prompts, 30/60/90/120-second choices, waveform-aware long-track looping, persistent model caching, and automatic insertion into My Assets.
• Automatic captions: Whisper small q8 ONNX with waveform-aware timing and conservative Chinese recognition cleanup.
• Smart framing: YOLOS tiny subject detection and MODNet portrait matting for smart crop, caption avoidance, and background removal across images and complete videos.
• AI Repair: browser-local MI-GAN watermark/object removal with multiple timed repair regions, plus NanoVSR 644K WebGPU 4× restoration for images and videos with synchronized before/after comparison.
• AI vocal separation: isolate vocals and place the instrumental stem on the music track without leaving the browser workflow.
• Digital human: JoyVASA audio-to-motion and LivePortrait neural rendering with WebGPU, 256px preview and 512px quality paths.
• Local-first inference: large models are lazy-loaded, revision-pinned, and cached by the service worker; supported workflows run without uploading project media to an editing backend.

Resilient model delivery

Browser AI models are mirrored on both Hugging Face and ModelScope. Timeline Studio uses ModelScope first for Chinese interfaces and domestic sessions, uses Hugging Face first elsewhere, remembers the first working source for the current runtime, and automatically falls back to the other source when needed. Cache identities are shared across both providers, so switching routes does not download the same revision twice.

• Stable Audio: Hugging Face · ModelScope
• Voice models: Hugging Face · ModelScope (mixed upstream licenses; see the repository model card)
• Timeline Studio ONNX models: Hugging Face · ModelScope
• Depth Anything V2 Small Q4F16: Hugging Face · ModelScope (Apache-2.0)
• Vocal remover: Hugging Face · ModelScope

Editing and export

• Contiguous main Visuals track plus timed picture-in-picture overlays.
• Direct canvas selection, movement, proportional resize, rotation, masks, filters, effects, animation, speed, and explicit keyframes, plus desktop four-way color grading with fully keyframeable temperature, tint, saturation, hue, wheel saturation, and luminance controls.
• Captions, stickers, voiceover, separated source audio, and music on independent timed tracks.
• CapCut-style snapping, alignment guides, clip menus, split/duplicate/delete, timeline zoom, undo/redo, and portable .timeline projects.
• Native media playback for a responsive preview; export uses a separate deterministic offline rendering path.
• WebCodecs MP4/WebM composition with shared preview/export geometry, audio mixing, captions, overlays, effects, and MediaRecorder fallback.
• Installable PWA with a cached app shell and multilingual UI.

Agent Skill

The repository includes the AI Video Editing Skill for Codex, Claude Code, Copilot and Gemini CLI, backed by edit-timeline-studio for planning, executing, and verifying editable video timelines.

It helps an agent:

• inspect media and preserve the user's editing brief;
• describe reversible edits with stable clip IDs and explicit timestamps;
• operate the hosted or local editor through the browser compatibility path;
• validate declarative edit plans with skills/edit-timeline-studio/scripts/validate_edit_plan.mjs;
• verify track placement, transitions, captions, overlays, audible audio, and final export artifacts;
• keep the editable .timeline project as the source of truth instead of returning only an opaque render.

The versioned headless command runner loads and inspects portable projects, validates revisioned JSON plans, applies supported operations transactionally, supports dry runs and idempotent operation IDs, and writes a new .timeline archive without rewriting its media files. It also renders the documented portable Visuals + Voiceover + Music subset to a verified H.264/AAC MP4. Browser control remains the compatibility path for operations that are not in the command registry yet. The browser WebMCP integration provides 21 tools for the open project: structured inspection, 26 reviewed visual/caption/audio/marker/framing operations, existing-asset and picture-in-picture insertion, rendered frame/audio sampling, local voiceover/transcription jobs, guarded undo, project saving, and real video export with prepared settings, progress, output receipts and cancellation.

npm run agent -- project.inspect /absolute/path/project.timeline
npm run agent -- track.inspect /absolute/path/project.timeline visuals
npm run agent -- clip.inspect /absolute/path/project.timeline visual-123
npm run agent -- transcript.inspect /absolute/path/project.timeline voice-123
npm run agent -- project.diff /absolute/path/edit-plan.json
npm run agent -- project.run /absolute/path/edit-plan.json
npm run agent -- project.render /absolute/path/render-request.json

The legacy inspect and run aliases remain available. The write registry supports ffprobe-backed, hashed visual/audio import to Visuals, Music, or the portable Voiceover slot, plus transactional timed edits, captions, source-accurate Visuals/Overlays, transitions, validated properties, track state, and ratio changes. Read commands return project, track, clip, transcript, media-inventory, and field-level predicted diffs. See the command contract for the plan envelope.

Install through the public skills.sh directory (the current CLI requires Node.js 22.20.0 or later):

npx skills add MartinDelophy/ai-video-editor --skill edit-timeline-studio

Or install it with GitHub CLI 2.90.0 or later:

# Claude Code
gh skill install MartinDelophy/ai-video-editor edit-timeline-studio --agent claude-code --scope user

# Codex
gh skill install MartinDelophy/ai-video-editor edit-timeline-studio --agent codex --scope user

To install the tested release instead of following the latest release, add --pin v1.0.8. Preview the Skill before installing with:

gh skill preview MartinDelophy/ai-video-editor edit-timeline-studio

Roadmap

• Now: expand the versioned command registry, harden deterministic offline export, and improve timeline editing reliability.