简体中文

AI MediaKit CLI — interface rebuilt for LLMs · agent-native · cloud + local

The agent-native command-line toolkit for audio & video. Run Volcengine's cloud AI and local editing through one unified command — built to be driven by AI agents (Claude Code, Trae, Cursor ...) or by you in the terminal.

mediakit-cli packs video enhancement, subtitle removal, and a full editing toolbox into a single tool. Heavy AI runs in the cloud; lightweight editing runs locally — switch with one flag, same command surface.

AI capabilities run in the cloud (elastic compute, async). Editing runs either in the cloud or locally (sync, zero cost) — pick per command with --cloud / --local.

npm install -g @volcengine/mediakit-cli
npx skills add volcengine/mediakit-cli -g -y # optional — install agent Skills (Claude Code / Trae / Cursor ...)
export MEDIAKIT_API_KEY=<your-api-key> # from the AI MediaKit console
# Cloud AI (async): enhance to 1080p, then poll for the result
mediakit-cli --cloud video enhance-video --video-url <url> --resolution 1080p
mediakit-cli shared query-task --task-id <task_id> --poll-complete
# Local editing (sync, no key needed): runs on your machine
mediakit-cli --local editing trim-video --video-url ./in.mp4 --start-time 3 --end-time 8

# npm (recommended, cross-platform — pulls the right build for your OS / arch)
npm install -g @volcengine/mediakit-cli
# npx (no install)
npx @volcengine/mediakit-cli version
# curl (macOS / Linux)
curl -fsSL https://raw.githubusercontent.com/volcengine/mediakit-cli/main/scripts/install.sh | bash

Pin a version or path: VERSION=<version> INSTALL_DIR="$HOME/.local/bin" curl -fsSL .../install.sh | bash

Verify: mediakit-cli doctor (checks cloud readiness + local tool deps + install hints).

mediakit-cli ships AI agent Skills that teach an agent how to call it — so a user can just say "enhance this video to 1080p and trim the best 5 seconds" and the agent orchestrates the commands.

# One command installs the Skills into every supported agent on your machine
npx skills add volcengine/mediakit-cli -g -y

This auto-detects and installs to 10+ runtimes — Claude Code, Trae (CN & Global), Cursor, Codex, Gemini CLI, GitHub Copilot, OpenCode, OpenClaw, Antigravity, and more.

Every capability is also MCP-compatible — mediakit-cli <domain> <tool> --schema emits a JSON Schema for MCP / Anthropic Tool Use / function-calling, no hand-written adapter needed.

• Two modes, one command surface. --cloud runs heavy AI in Volcengine's cloud (elastic compute, async task_id); --local runs deterministic editing locally (sync, zero cloud cost). Default mode is cloud-first; per-command flags override it.
• Command structure: mediakit-cli [--cloud|--local] <domain> <tool> [flags] — domains are editing · video · shared.
• Outputs: cloud results are returned as URLs; local results write to ~/.mediakit/temp (override with --output-path or MEDIAKIT_OUTPUT_PATH).

• Volcengine AI MediaKit product docs & pricing: https://www.volcengine.com/docs/6448
• Full command reference & FAQ: see the docs site.

make build # local build → .mediakit/build/dev/mediakit-cli
make build-all # all platforms
make snapshot # snapshot release

Releases are produced via .goreleaser.yml; npm distribution via package.json + scripts/install.js; curl install via scripts/install.sh.

This project is open-sourced under the MIT License.

This software calls MediaKit APIs at runtime. Use of these APIs is subject to the following terms and privacy policies:

• Video Cloud Service Special Terms
• Intelligent Processing Service Billing Rules
• Intelligent Processing Service Level Agreement