Official vendor OpenAPI document · agent-readyMediaVideo Processingbearer, apiKey135 EndpointsREST
For 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.
Use for: I want to turn a text brief into a finished short-form video, Generate a video clip from a prompt, Search my own footage for usable moments, Render a composition to a 1080x1920 MP4
Not supported: Does not handle live streaming, podcast distribution, or social publishing. Use for composing, rendering, and exporting video projects only.
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.
Install Jentic One Beta
Connect the CueFrame API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the CueFrame API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
1
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fcueframe.ai%2Fcueframe" | sh2
Step 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fcueframe.ai%2Fcueframe" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
Capabilities
What an agent can do with CueFrame API.
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
Patterns agents use CueFrame API for, with concrete tasks.
★ 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.
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.
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.
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
135 endpoints — the cueframe api composes, renders, and exports short-form video projects from raw footage using an agent-driven director workflow.
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
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
Jentic AI Readiness Score
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.
C
CueFrame API
- Foundational (C+)57/100
46
Foundational Compliance69
Developer Experience & Jentic Compatibility47
AI-Readiness & Agent Experience73
Agent Usability55
Security71
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.2
Show dimension breakdown
46
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: DSignals: 4
83%
Lint Results
Aggregated quality score from linter diagnostics, weighted by severity.
100%
Resolution Completeness
Percentage of `$ref` references that resolve successfully.
0%
Specification Validity
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
0%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
69
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: B+Signals: 4
0%
Example Density
How richly the API is illustrated with examples.
100%
Example Validity
Percentage of examples that conform to their schemas.
74%
Response Coverage
Percentage of operations with complete response definitions (success, client error, server error).
100%
Tooling Readiness
Health of API ingestion, bundling, and resolution within Jentic pipelines.
47
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: D+Signals: 4
37%
Description Coverage
Coverage of descriptions across API elements.
0%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
97%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
55%
Summary Coverage
Coverage of summaries across operations/tags/info.
73
Agent Usability
Functional utility, complexity comfort, and AI orchestration readiness.
Grade: A-Signals: 1
73%
Complexity Comfort
Agent comfort level based on API operational and structural complexity.
55
Security
Trust, risk posture, and security compliance.
Grade: CSignals: 1
55%
Authentication Strength
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
71
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: A-Signals: 1
71%
Descriptive Richness
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>Why Jentic?
What agents get from Jentic-routed access to this vendor.
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 isolation
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.
Intent-based discovery
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
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using CueFrame API through Jentic.
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.
GET STARTED