canonical: https://jentic.com/apis/cueframe.ai/cueframe

# CueFrame API

The CueFrame API composes, renders, and exports short-form video projects from raw footage using an agent-driven Director workflow. It ingests media through signed uploads or URL import, runs semantic search and clip-suggestion analysis over your own footage, and builds compositions that you can preview, score, and render to MP4 or export as Final Cut Pro and Premiere Pro timelines. Brand kits, reusable templates, and webhook delivery let an agent produce on-brand videos and track every render job to completion.

## For AI agents

Compose, render, and export short-form videos from raw footage: generate media with AI, search your own clips, apply brand kits and templates, and deliver finished MP4s or editor timelines. Tracks render and compose jobs asynchronously with webhook callbacks.

## Scope

Does not handle live streaming, podcast distribution, or social publishing. Use for composing, rendering, and exporting video projects only.

## Capabilities

- Compose multi-scene video timelines from a brief using the Director workflow
- Render projects to MP4 and stream render-job status over server-sent events
- Generate video, image, or Manim animation media from a prompt
- Search your own footage semantically and turn clip suggestions into compositions
- Export finished projects as Final Cut Pro (FCPXML) and Premiere Pro timelines
- Apply brand kits and reusable templates so every render stays on-brand
- Deliver render and job events to registered webhook endpoints

## Use cases

### Agent-Driven Video Production

An AI agent connected through Jentic can turn a text brief into a finished short-form video: it creates a project, imports source footage, starts a Director compose job, scores the resulting composition, and renders it to MP4. CueFrame runs compose and render work asynchronously and reports progress over server-sent event streams and webhooks, so the agent can poll or subscribe until the video is ready.

Example prompt: Create a project, import a source clip from a URL, start a compose job from a brief, then render the selected composition to a 1080x1920 MP4 and return the output URL

### Footage Search and Clip Suggestions

Teams with large footage libraries use CueFrame to find usable moments without scrubbing timelines. Semantic search over an organisation's own media returns ranked matches, and clip-suggestion analysis proposes cut points that can be promoted straight into a composition. Transcripts, face detection, and derived facts give an editor or agent the context to assemble a rough cut quickly.

Example prompt: Run a semantic search for 'product demo closeups' over the org's footage and create a composition from the top clip suggestion

### Multi-Format Delivery and Editor Handoff

CueFrame renders a single composition to multiple aspect ratios and hands off to professional editors when needed. A project can be derived into reframed sibling compositions for vertical, square, and landscape, rendered to MP4 with a share link, or exported as Final Cut Pro and Premiere Pro timelines so a human editor finishes in their own tool. Brand kits keep fonts, colours, and logos consistent across every variant.

Example prompt: Derive a 1x1 and a 9x16 sibling composition from a finished 16x9 project and create a Final Cut Pro export for the vertical cut

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | `/v1/projects` | Create a project |
| POST | `/v1/projects/{id}/compose` | Start a Director compose workflow |
| POST | `/v1/projects/{id}/renders` | Create a render job |
| GET | `/v1/projects/{id}/renders/{renderId}` | Get a render job |
| POST | `/v1/media/generate` | Generate media with AI |
| GET | `/v1/media/search` | Semantic search over the org's footage |
| POST | `/v1/projects/{id}/exports/fcpxml` | Create a Final Cut Pro export |

## Key resources

- **Projects and Compositions** — Create projects and build, validate, and version the compositions that define each video.
- **Media** — Upload, import, search, and analyse source footage, including transcripts and clip suggestions.
- **Renders and Exports** — Queue MP4 renders and export projects to Final Cut Pro and Premiere Pro timelines.
- **Brand Kits and Templates** — Store brand tokens and reusable templates to keep output on-brand.
- **Webhooks** — Register endpoints to receive render and job delivery events.

## AI readiness

This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.

- **Score:** 57 / 100
- **Maturity:** Foundational
- **Dimensions:**
  - Foundational Compliance: 46 / 100
  - Developer Experience & Jentic Compatibility: 69 / 100
  - AI-Readiness & Agent Experience: 47 / 100
  - Agent Usability: 73 / 100
  - Security: 55 / 100
  - AI Discoverability: 71 / 100
- **View full report:** https://jentic.com/apis/cueframe.ai/cueframe/scorecard
- **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/
- **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview

### Score it yourself

Every API in the directory is allowlisted, so you can re-score it with no key required.

- **Score your own API:** https://jentic.com/scorecard.md
- **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md

```sh
npx @jentic/api-scorecard-cli score <openapi-url>
```

## Why Jentic

- **Setup:** Wiring the CueFrame API by hand means handling its bearer keys, the separate x402 payment-signature header for priced endpoints, asynchronous compose and render jobs, and server-sent event streams for status. Through Jentic you install once, import CueFrame from the API Directory, store the key once, and your agent calls it.
- **Permission scoping:** CueFrame puts the project id in the URL path, so a rule can pin your agent to the project operations it needs and leave out destructive ones like project deletion or share-link revocation. Because every resource is org-scoped and cross-org reads return a not-found response, a scoped key cannot reach another organisation's media.
- **Credential handling:** Your CueFrame key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'generate a video clip' or 'export to Premiere', and Jentic returns the matching CueFrame operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **BlitzReels** — AI-driven short-form reel generation, focused on auto-editing rather than full compose-and-export control.
- **AI Content Drop** — Generates AI video content from prompts, with less emphasis on multi-format rendering and brand kits.
- **api.video** — Video hosting, streaming, and delivery that pairs with the CueFrame API once a render is finished.

## FAQ

### What authentication does the CueFrame API use?

The CueFrame API authenticates with a bearer API key per its OpenAPI spec: you send an Authorization header carrying a key prefixed cf_live_ or cf_test_. Priced endpoints can additionally accept an x402 payment signature through the PAYMENT-SIGNATURE header, and a few endpoints such as the health check and the skills listing are public. Through Jentic the key is stored once, encrypted, by your own Jentic One instance and injected at call time.

### Can I generate video from a text prompt with the CueFrame API?

Yes. The media generation endpoint produces video, image, or Manim animation media from a prompt, and the Director compose workflow assembles those assets into a timeline you can render to MP4. An agent can import existing footage by URL, generate new shots, and combine both in one composition.

### What are the rate limits for the CueFrame API?

The OpenAPI spec does not define rate limits for the CueFrame API. Check the CueFrame documentation at https://docs.cueframe.ai for current limits and plan tiers.

### Is there a CueFrame MCP server?

You don't need an MCP server to give your agent the CueFrame API. Jentic connects it directly from the API Directory: import CueFrame, store your key once, and your agent calls its compose, render, and export operations. You skip loading another server's tool definitions into the agent's context.

### Can I limit what my agent is allowed to do with the CueFrame API?

Yes. Write a rule that allows only the operations the task needs, such as creating projects, composing, and rendering, so destructive operations like deleting projects or revoking share links are not included unless you add them. CueFrame also scopes every resource to your organisation and returns a not-found response for cross-org access, so an agent cannot reach another org's projects. Every call the agent makes is logged.

### How do I render a video with the CueFrame API through Jentic?

Search Jentic for 'compose and render a short video', and it returns the matching CueFrame operations with their input schemas. Your agent creates a project, imports media, starts a compose job, and renders the result to MP4, polling the render-job status stream until the file is ready. To run it on your own infrastructure, install Jentic One from its GitHub repo.