Snapshot 2026-08-03 23:56:39 UTC · version 1
JSON in, JSON out: every command reads and writes the local draft store directly, with no MCP server or HTTP daemon. On newer CapCut versions it detects and synchronizes every readable timeline target instead of assuming `draft_content.json` is the only source of truth. That give
English | 中文
Disclaimer: This is an independent, community-maintained project. It is not affiliated with, sponsored by, or endorsed by CapCut, JianYing, or ByteDance Ltd. "CapCut" and "JianYing" (剪映) are trademarks of ByteDance Ltd. All product names, logos, and brands are the property of their respective owners and are used here only for identification (nominative) purposes.
An independent CLI for CapCut / JianYing that any LLM agent can drive — zero dependencies, no server, both namespaces in one binary.
JSON in, JSON out: every command reads and writes the local draft store directly, with no MCP server or HTTP daemon. On newer CapCut versions it detects and synchronizes every readable timeline target instead of assuming draft_content.json is the only source of truth. That gives any model (Claude, DeepSeek, GLM, Kimi) a deterministic boundary for inspection, building, subtitles, captions, translation, and long-form cuts.
Use it three ways:
npm install -g capcut-cli, then capcut <command> <project>import { loadDraft, lintDraft, saveDraft } from "capcut-cli" (typed, zero-dep)capcut serve reads JSONL jobs from stdin, for n8n / Make / CozeNew in v0.16.0: first-class support for the newer Mac draft layout (
draft_info.json-primary) across edits,sync-timelines,register, anddiagnose, version-aware mask writes with--mask-fieldand a lint mismatch check, the cut exported as OpenTimelineIO (export-timeline) for DaVinci Resolve handoff, learning store effect ids from app-authored drafts (harvest-enums), VFR and unreadable-media checks inlintwith concrete ffmpeg fixes, and safe auto-repair of dangling companion refs (lint --fix). Full details in the changelog.
New in v0.15.0: a write-time version guard that refuses beyond-evidence or known-broken drafts unless
--force-write, in-place segment deletion with orphaned-material cleanup (remove), raw store resource ids, working--intensity, and whole-timeline--fullonadd-filter/add-effect, experimental per-segment--bindonadd-effect, andlintunknown-slug coverage extended to transitions, masks, sound effects, bubbles, and fonts. Full details in the changelog.
Prerequisites: Node ≥ 18 (built-ins only — no native modules). Optional tools unlock specific commands: Whisper for caption, FFmpeg for render, ffprobe for automatic media metadata, and ANTHROPIC_API_KEY for translate.
npm install -g capcut-cli # or: npx capcut-cli <command>
Build from source instead: git clone https://github.com/renezander030/capcut-cli && cd capcut-cli && npm install && npm run build (then npm link to expose capcut).
capcut doctor # verify Node, FFmpeg, whisper, draft dirs
capcut quickstart my-first --video clip.mp4 # create + add input + lint, prints the "open in CapCut" step
capcut info ./my-first/ # inspect the draft (add -H for a table)
Then open the project in CapCut to review and render. Every short-video platform forbids automated upload, so the publish click stays human.
JSON by default (pipe to jq); add -H for a human-readable table. Pass --jianying to use the JianYing enum namespace. Run capcut <command> --help for full flags.
| Group | Commands |
|---|---|
| Inspect | info · tracks · materials · version · lint |
| Browse / drill in | segments · texts · segment · material |
| Create | init · quickstart · compile (build a draft from a JSON spec) |
| Preview | render (low-res ffmpeg proxy — not CapCut's final render) |
| Add | add-video · add-audio · add-text (Wikimedia URLs supported, license-checked) |
| Edit / animate | trim · speed · volume · transitions · masks · text/image animations · easing curves |
| Templates | apply and extract reusable layouts · make-preset (portable text-style presets) |
| Subtitles & i18n | caption · import-srt · export-srt (line/word SRT + VTT) · translate (multi-language draft clone) |
| Effects | sfx · chroma (chroma key) |
| Long-form → short | cut · detect-scenes (ffmpeg scene-cut detection) |
| Automation | serve (stateless JSONL runner) · migrate · doctor · sync-timelines (8.7 mirror repair) |
Full reference for every command, option, and exit code: docs/command-reference.md.
CapCut/JianYing store each project as local JSON. capcut-cli loads that store, validates against a version-aware schema, applies your edit, and writes it back atomically (with a .bak). No project files are uploaded anywhere; nothing runs as a service. See docs/version-support.md for the CapCut/JianYing versions and schema flags it understands.
CapCut™ and JianYing™ (剪映) are trademarks of ByteDance Ltd. This project is unofficial and is not affiliated with or endorsed by ByteDance; the marks are used nominatively to describe interoperability.
MIT
Sign in to join the discussion.
Snapshot 2026-08-03 23:56:39 UTC · version 1
JSON in, JSON out: every command reads and writes the local draft store directly, with no MCP server or HTTP daemon. On newer CapCut versions it detects and synchronizes every readable timeline target instead of assuming `draft_content.json` is the only source of truth. That give
English | 中文
Disclaimer: This is an independent, community-maintained project. It is not affiliated with, sponsored by, or endorsed by CapCut, JianYing, or ByteDance Ltd. "CapCut" and "JianYing" (剪映) are trademarks of ByteDance Ltd. All product names, logos, and brands are the property of their respective owners and are used here only for identification (nominative) purposes.
An independent CLI for CapCut / JianYing that any LLM agent can drive — zero dependencies, no server, both namespaces in one binary.
JSON in, JSON out: every command reads and writes the local draft store directly, with no MCP server or HTTP daemon. On newer CapCut versions it detects and synchronizes every readable timeline target instead of assuming draft_content.json is the only source of truth. That gives any model (Claude, DeepSeek, GLM, Kimi) a deterministic boundary for inspection, building, subtitles, captions, translation, and long-form cuts.
Use it three ways:
npm install -g capcut-cli, then capcut <command> <project>import { loadDraft, lintDraft, saveDraft } from "capcut-cli" (typed, zero-dep)capcut serve reads JSONL jobs from stdin, for n8n / Make / CozeNew in v0.16.0: first-class support for the newer Mac draft layout (
draft_info.json-primary) across edits,sync-timelines,register, anddiagnose, version-aware mask writes with--mask-fieldand a lint mismatch check, the cut exported as OpenTimelineIO (export-timeline) for DaVinci Resolve handoff, learning store effect ids from app-authored drafts (harvest-enums), VFR and unreadable-media checks inlintwith concrete ffmpeg fixes, and safe auto-repair of dangling companion refs (lint --fix). Full details in the changelog.
New in v0.15.0: a write-time version guard that refuses beyond-evidence or known-broken drafts unless
--force-write, in-place segment deletion with orphaned-material cleanup (remove), raw store resource ids, working--intensity, and whole-timeline--fullonadd-filter/add-effect, experimental per-segment--bindonadd-effect, andlintunknown-slug coverage extended to transitions, masks, sound effects, bubbles, and fonts. Full details in the changelog.
Prerequisites: Node ≥ 18 (built-ins only — no native modules). Optional tools unlock specific commands: Whisper for caption, FFmpeg for render, ffprobe for automatic media metadata, and ANTHROPIC_API_KEY for translate.
npm install -g capcut-cli # or: npx capcut-cli <command>
Build from source instead: git clone https://github.com/renezander030/capcut-cli && cd capcut-cli && npm install && npm run build (then npm link to expose capcut).
capcut doctor # verify Node, FFmpeg, whisper, draft dirs
capcut quickstart my-first --video clip.mp4 # create + add input + lint, prints the "open in CapCut" step
capcut info ./my-first/ # inspect the draft (add -H for a table)
Then open the project in CapCut to review and render. Every short-video platform forbids automated upload, so the publish click stays human.
JSON by default (pipe to jq); add -H for a human-readable table. Pass --jianying to use the JianYing enum namespace. Run capcut <command> --help for full flags.
| Group | Commands |
|---|---|
| Inspect | info · tracks · materials · version · lint |
| Browse / drill in | segments · texts · segment · material |
| Create | init · quickstart · compile (build a draft from a JSON spec) |
| Preview | render (low-res ffmpeg proxy — not CapCut's final render) |
| Add | add-video · add-audio · add-text (Wikimedia URLs supported, license-checked) |
| Edit / animate | trim · speed · volume · transitions · masks · text/image animations · easing curves |
| Templates | apply and extract reusable layouts · make-preset (portable text-style presets) |
| Subtitles & i18n | caption · import-srt · export-srt (line/word SRT + VTT) · translate (multi-language draft clone) |
| Effects | sfx · chroma (chroma key) |
| Long-form → short | cut · detect-scenes (ffmpeg scene-cut detection) |
| Automation | serve (stateless JSONL runner) · migrate · doctor · sync-timelines (8.7 mirror repair) |
Full reference for every command, option, and exit code: docs/command-reference.md.
CapCut/JianYing store each project as local JSON. capcut-cli loads that store, validates against a version-aware schema, applies your edit, and writes it back atomically (with a .bak). No project files are uploaded anywhere; nothing runs as a service. See docs/version-support.md for the CapCut/JianYing versions and schema flags it understands.
CapCut™ and JianYing™ (剪映) are trademarks of ByteDance Ltd. This project is unofficial and is not affiliated with or endorsed by ByteDance; the marks are used nominatively to describe interoperability.
MIT
Sign in to join the discussion.