{"slug": "timeline-studio", "title": "Timeline Studio", "summary": "Timeline Studio, a local-first AI video editor that runs in the browser, has been released as an open-source project. The editor combines a multi-track timeline with browser-side AI voiceovers, automatic captions, vision tools, talking-avatar generation, and deterministic offline export, supporting multilingual voiceovers and local-first inference without uploading media to a backend.", "body_md": "**English** | [中文](/MartinDelophy/ai-video-editor/blob/main/README.zh-CN.md)\n\nTimeline Studio is a local-first AI video editor that runs in the browser. It combines a CapCut-style multi-track timeline with browser-side AI voiceovers, automatic captions, vision tools, talking-avatar generation, and deterministic offline export.\n\n[Open the editor](https://video-editor.ai-creator.top/) · [Watch the demo](https://youtu.be/mUXduGpBmwE) · [Hugging Face Space](https://huggingface.co/spaces/haixin/timeline-studio)\n\n**Multilingual voiceover:** Chinese Piper/VITS ONNX voices, English Kokoro 82M, and browser Piper voices for German, Spanish, French, Italian, and Brazilian Portuguese.**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 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.\n\n- Contiguous main Visuals track plus timed picture-in-picture overlays.\n- Direct canvas selection, movement, proportional resize, rotation, masks, filters, effects, animation, speed, and explicit keyframes.\n- Captions, stickers, voiceover, separated source audio, and music on independent timed tracks.\n- CapCut-style snapping, alignment guides, clip menus, split/duplicate/delete, timeline zoom, undo/redo, and portable\n`.timeline`\n\nprojects. - Native media playback for a responsive preview; export uses a separate deterministic offline rendering path.\n- WebCodecs MP4/WebM composition with shared preview/export geometry, audio mixing, captions, overlays, effects, and MediaRecorder fallback.\n- Installable PWA with a cached app shell and multilingual UI.\n\nThe repository includes [ edit-timeline-studio](/MartinDelophy/ai-video-editor/blob/main/skills/edit-timeline-studio/SKILL.md), a Codex-compatible Skill for planning, executing, and verifying editable video timelines.\n\nIt helps an agent:\n\n- inspect media and preserve the user's editing brief;\n- describe reversible edits with stable clip IDs and explicit timestamps;\n- operate the hosted or local editor through the browser compatibility path;\n- validate declarative edit plans with\n`skills/edit-timeline-studio/scripts/validate_edit_plan.mjs`\n\n; - verify track placement, transitions, captions, overlays, audible audio, and final export artifacts;\n- keep the editable\n`.timeline`\n\nproject as the source of truth instead of returning only an opaque render.\n\nThe current Skill is honest about its boundary: browser-driven editing is available today, while the versioned headless command runner described in its command contract is the next automation layer.\n\nRequirements: Node.js 20+ and a modern Chromium browser. WebGPU is recommended for the heaviest AI workflows.\n\n```\ngit clone https://github.com/MartinDelophy/ai-video-editor.git\ncd ai-video-editor\nnpm install\nnpm run dev\n```\n\nOpen the local URL printed by Vite. The first AI run may download model files; later runs reuse the browser cache.\n\n```\nnpm test\nnpm run build\nnpm run preview\n```\n\nRun the complete repository check with:\n\n```\nnpm run check\n```\n\nThe included [ netlify.toml](/MartinDelophy/ai-video-editor/blob/main/netlify.toml) builds with\n\n`npm run build`\n\n, publishes `dist`\n\n, enables the cross-origin isolation headers required by browser AI/media workers, and provides the SPA fallback.\n\n```\nnpx netlify-cli deploy --prod --dir=dist\n```\n\n", "url": "https://wpnews.pro/news/timeline-studio", "canonical_source": "https://github.com/MartinDelophy/ai-video-editor", "published_at": "2026-07-18 08:12:12+00:00", "updated_at": "2026-07-18 08:21:06.481013+00:00", "lang": "en", "topics": ["ai-tools", "artificial-intelligence", "computer-vision", "natural-language-processing", "generative-ai"], "entities": ["Timeline Studio", "CapCut", "Piper", "VITS", "Kokoro", "Whisper", "YOLOS", "MODNet"], "alternates": {"html": "https://wpnews.pro/news/timeline-studio", "markdown": "https://wpnews.pro/news/timeline-studio.md", "text": "https://wpnews.pro/news/timeline-studio.txt", "jsonld": "https://wpnews.pro/news/timeline-studio.jsonld"}}