Kling for Meta Muse
Kling AI video generation with client-side JWT auth: text-to-video, image-to-video, status polling, clip extend, lip-sync.
Generate top-tier video with Kling's official open platform: text-to-video, image-to-video, clip extension, and lip-sync, plus Kolors image generation and talking-avatar endpoints on the same platform. Use when Michael wants the highest-quality AI video clips. Kling is also reachable through fal.ai with simpler auth (trade-off: fal's markup).
View original source ↗How to set it up
Paste a promptDraft — these instructions come from the linked source and have not been independently live-tested by OpenTools.
Before you start
- access key + secret key pair via the secure credential flow
Steps
- Paste the install prompt into a chat with Muse.
- Muse fetches the pinned SKILL.md and the 2 files in its manifest.
- Authorize your own account through Muse’s secure credential flow.
- Have Muse run the status check shown in the source skill.
Prompt to paste into Muse
Install this connector: https://raw.githubusercontent.com/bluman1/muse-connectors/6e31fd44a71f9f28377a1460e64cd7483c3cce22/connectors/kling/SKILL.md Read its Files manifest and install exactly those files. Collect credentials through Muse's secure credential flow; never ask me for raw keys in chat. Run the skill's status check and report the result.
Account access: access key + secret key pair via the secure credential flow (`credentials.request_api_access`); created at app.klingai.com/global/dev. Stored as ONE value in `access_key:secret_key` format.
Allowed hosts: api.klingai.com
Confirm it works: `bin/kling.py auth` (must return `"ok": true`). Auth is unusual: the CLI splits the credential on the first colon, mints a short-lived HS256 JWT per request with stdlib hmac (iss = access key, exp ~30 min), and sends `Authorization: Bearer <jwt>`. The secret never leaves the vault path.
Services it connects with
These are the services the connector uses. The publisher is identified separately.
Kling