English | 中文 | 日本語 | 한국어 | Español | Français | Deutsch | Português | ไทย | Tiếng Việt | Русский
Try the Anna edition for AI-assisted editing and project continuity:
- Describe your edit to Anna, review a plan based on your brief and clip metadata, then apply supported clip ordering and simple 1× video trims.
- Projects and media save automatically to Anna cloud storage and can resume with the same Anna account in another browser. Local project checkpoints provide an additional recovery option.
- Refine the editable multi-track timeline, add AI voiceovers and manual captions, and export MP4 using an available browser encoder.
This desktop preview plans from metadata, without analyzing video frames or audio; local AI features depend on the Anna container’s capabilities.
遇到任何问题，欢迎扫码进群交流。我们急需你的建议和反馈！
Run into any issues? Scan the QR code to join our WeChat group. We really need your suggestions and feedback!
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.
- 2026-11-04 — Added Line art beside Depth map in Effects: adjustable detail, line weight and inversion with a live preview. Images become PNG assets and trimmed/speed-mapped videos become 24 fps WebM assets with source audio, saved to My assets without automatic insertion. Includes all 13 interface languages and mobile controls. Fixed playback when only picture-in-picture clips remain on the timeline.
- 2026-11-03 — Added desktop File, Edit, Clip, View and Help menus wired to existing editing, preview, proxy and help actions, with keyboard navigation and all 13 interface languages. Phones and tablets retain the compact menu layout. Fixed undo/redo during media preparation, source-time preservation when splitting speed curves, and separated-audio playback synchronization. Keyboard menu focus is now assigned after the dropdown mounts. Proxy controls now live in View, with actual playback-source status, separate cache management, distinct icons across every menu, and a mobile sheet localized in all 13 languages.
- 2026-11-03 — Added browser-local 1280px video proxies for editing, with background generation, source-timestamp validation, reusable local caching and original-media export. Preview mode can be switched back to originals; exact timeline thumbnails continue to use source media.
- 2026-11-02 — Added compact icon-based alignment menus and split screens that include the main picture and visible overlays, with two-, three- and four-picture layouts, shared preview/export cropping and one-step undo. Agents can now invoke both features through shared CLI, STDIO MCP and browser preview/apply commands, documented in the editing Skill.
- 2026-10-30 — Added preview-video context menus for canvas alignment, fit/fill, overlay start/end alignment, and manual reference-frame synchronization, with undo and locked-track protection. See the public Roadmap for planned work, Releases for shipped changes, and Issues for focused tasks and bugs.
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
Visual analysis, keyframes, captions, and export.
timeline-studio-demo.mp4
Timed watermark removal with before/after review.
ai-voiceover.2.mp4
timeline-studio-ai-voiceover-demo.mp4
- 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.
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
- 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
.timelineprojects. - 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.
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
.timelineproject 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.jsonThe 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-studioOr 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 userTo 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- Now: expand the versioned command registry, harden deterministic offline export, and improve timeline editing reliability.
- Next: expand headless render parity and the reviewed browser WebMCP command subset.
- Later: add collaborative review workflows, a plugin extension surface, and more locally verified AI models.
Roadmap priorities are shaped in GitHub Discussions. Feature requests and real-world workflow feedback are welcome.
Timeline Studio is looking for contributors interested in browser media, WebCodecs, WebGPU/ONNX, timeline UX, localization, testing, and documentation.
- Try the live editor and report reproducible bugs in Issues.
- Join Discussions to propose features, share projects, or help prioritize the roadmap.
- Read the contribution guide for setup, validation, and first-contribution guidance.
- Contributions of focused fixes, tests, translations, documentation, and example projects are especially useful.
Requirements: Node.js 20+ and a modern Chromium browser. WebGPU is recommended for the heaviest AI workflows.
git clone https://github.com/MartinDelophy/ai-video-editor.git
cd ai-video-editor
npm install
npm run devOpen the local URL printed by Vite. The first AI run may download model files; later runs reuse the browser cache.
npm run build
npm run previewRun the complete repository check with:
npm run checkThe included netlify.toml builds with npm run build, publishes dist, enables the cross-origin isolation headers required by browser AI/media workers, and provides the SPA fallback.
npx netlify-cli deploy --prod --dir=distIf this project helps you, please consider giving it a ⭐ Star. If you encounter a problem, please open an Issue.
Join our Discord community to ask questions, share feedback, and connect with other users and contributors.
Timeline Studio's original source code is licensed under the MIT License.
The MIT License does not automatically apply to third-party models, model weights, datasets, fonts, stock media, or other bundled or remotely downloaded assets. Those materials remain subject to their respective upstream licenses and terms, regardless of where they are hosted or how they are downloaded or integrated. Review MODEL_LICENSES.md before redistribution or commercial use.
