ClipReel for Agents

Automate video editing with AI agents

Use the ClipReel REST API to automate product demos, social cutdowns, captions, and reviewable edits with durable render jobs.

Connect an agent

Try the edit on real footage

Compare the eight-second source shot and the six-second edit. Open the sample project with the request ready to send.

Trim the first two seconds, add the title “A day on the ridge” for three seconds, make the grade cooler, and fade out in the last half second.
Try in ClipReel Download the source clip
Original shot
Trim, title, and fade

Connect to ClipReel

Create a scoped token, save it as CLIPREEL_API_TOKEN, and configure your client. Use a project read, project write, and job token for the walkthrough.

curl https://www.clipreel.com/api/v1/projects \
  -H "Authorization: Bearer $CLIPREEL_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"name":"Product walkthrough"}'

Automate a product demo in stages

Create a project for each launch and import the original screen recordings. Queue edit_by_prompt with a clear opening, a target duration, and caption requirements. Submit an idempotency key for each job so a retry can recover the original result.

Build social versions from the approved cut

Pin the same saved revision in each export_video request and send a distinct key for 16:9, 9:16, or square. Poll the job resource for the next status. Use the edit link to open the same footage, cuts, captions, and effects before asking for another export.

Handle errors and permissions in your integration

Use scoped account tokens and upload directly to the signed URL. Verify callback signatures against the raw request body before reading a completion. Use the stable job ID to handle retries. For a partner app, create one scoped embed session for its exact origin and project.

REST workflows

Send JSON with Authorization: Bearer $CLIPREEL_API_TOKEN. For a file import, send the declared filename, media type, byte length, and duration to POST /tools/import_media. Upload the file with the same content type and length to the returned URL.

Draft a launch cut

POST https://www.clipreel.com/api/v1/tools/edit_by_prompt
{
  "projectId": "PROJECT_ID",
  "prompt": "Remove pauses, add captions, and cut a 45-second launch video",
  "idempotencyKey": "launch-v1-edit"
}

Generate or import caption cues

Queue POST /tools/transcribe_video with the project ID. Then poll GET /jobs/JOB_ID. Pass returned result.cues to POST /tools/add_captions with a style such as white or lime. Use the same cue object for timestamps you supply yourself.

Export a vertical cut

POST https://www.clipreel.com/api/v1/tools/export_video
{
  "projectId": "PROJECT_ID", "revision": 7,
  "aspect": "9:16", "resolution": "720p",
  "idempotencyKey": "launch-v1-vertical", "webhookId": "WEBHOOK_ID"
}

Verify signed callbacks

Register your HTTPS endpoint at POST /webhooks with {"url":"https://partner.example.com/clipreel"}. Store the returned signing secret. Compute HMAC-SHA256 over the Unix timestamp, a period, and the raw request body. Compare in constant time with v1 in the ClipReel-Signature header. Reject timestamps more than five minutes old. Treat ClipReel-Delivery as the deduplication ID. Poll for fresh signed media links.

Embed the same editable project

POST https://www.clipreel.com/api/v1/embed-sessions
{
  "projectId": "PROJECT_ID",
  "origin": "https://partner.example.com",
  "permission": "edit"
}

Load embedUrl in an iframe on the registered origin. Sessions last 20 minutes and inherit the token’s permissions. Set permission to view for a review-only session. Open in ClipReel takes the editor back to the private project in the full workspace.

Client setup and workflows

Video editing in Claude Code

Ask Claude Code to turn recordings into an editable cut. Review a preview, then open the same project in ClipReel.

Claude Code setup
Trim the first two seconds.

Video editing MCP server

Connect an MCP client to ClipReel to create projects, propose timeline edits, review previews, and export editable cuts.

MCP setup

Edit product videos from Cursor

Use Cursor and ClipReel to turn product walkthrough recordings into an editable video with captions and multiple export formats.

Cursor workflow

Automate video editing with AI agents

Use the ClipReel REST API to automate product demos, social cutdowns, captions, and reviewable edits with durable render jobs.

REST API guide

Hosted jobs use your ClipReel plan. See chat edits and video credits by plan.