Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the BlitzReels 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.
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%2Fblitzreels.com%2Fblitzreels" | shStep 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%2Fblitzreels.com%2Fblitzreels" | 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.
What an agent can do with BlitzReels API.
Create short-form clips from a source video
Preview a YouTube source before clipping it
Export a clip to a finished video
List and apply clip presets for format and style
Organize clips in clipping projects and a workspace media library
GET STARTED
Generate caption emoji accents for a project
Validate an API key before running a clip batch
Patterns agents use BlitzReels API for, with concrete tasks.
★ Agent-driven clip creation
An AI agent turns a long video into publishable short-form clips. Through Jentic the agent previews a YouTube source, creates clips with a chosen preset, and exports each one to a finished video. The clips land in a clipping project where the agent can read their status before handing them off.
Preview a YouTube source, create clips with a vertical preset, and export the accepted clips to finished videos
Review-and-promote workflow
A creator keeps a human in the loop before a clip ships. The API lets a clip be rejected or repaired after visual review, and a visually accepted export can be promoted as a managed delivery. An agent can create the batch, surface the clips for review, and promote only the approved ones.
List the clips in a batch, promote the exports a reviewer accepted, and reject the rest
Media library management
A team keeps its source media organized across projects. The API manages a workspace media library with folders and assets, and exposes the latest clip batch for a media asset, so an agent can find a source, clip it, and track the resulting batch. Batch and asset operations keep the library tidy between runs.
Find a media asset, read its latest clip batch, and create new clips from the same source
275 endpoints — the blitzreels api creates ai-powered short-form video clips from a source and exports them to finished videos.
METHOD
PATH
DESCRIPTION
/clips
List clips
/clips
Create clips
/clips/{clip_id}
Get a clip
/clips/{clip_id}/export
Export a clip
/clips/presets
List available clip presets
/clips/source-preview
Preview a YouTube source before clipping
/clipping-projects
List clipping projects
/auth/validate
Validate API key
/clips
List clips
/clips
Create clips
/clips/{clip_id}
Get a clip
/clips/{clip_id}/export
Export a clip
/clips/presets
List available clip presets
/clips/source-preview
Preview a YouTube source before clipping
/clipping-projects
List clipping projects
/auth/validate
Validate API key
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the BlitzReels API by hand means handling its API key in the Authorization header as a bearer value, polling clip and export jobs across a large surface, and tracking clip batches and media assets yourself. Through Jentic you install once, import it from the API Directory, store the key once, and your agent calls it.
Permission scoping
The BlitzReels API puts the clip id in the URL path (/clips/{clip_id}), so a rule can pin your agent to the clip operations it needs: it can create and export clips and read their status without reaching workspace recovery or batch-delete operations. You choose the operations it may call, so destructive ones like deleting a clip or emptying a media folder are not included unless you add them.
Credential isolation
Your BlitzReels API key is held 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 'create short-form clips' or 'export a video clip', and Jentic returns the matching BlitzReels operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using BlitzReels API through Jentic.
What authentication does the BlitzReels API use?
The BlitzReels API authenticates with an API key sent in the Authorization header as a bearer value per its OpenAPI spec. Through Jentic the key is injected at call time by your own Jentic One instance, so it never enters the agent's prompt or logs.
Can I create clips from a YouTube video with the BlitzReels API?
Yes. The source-preview operation previews a YouTube source before clipping, and the create-clips operation generates short-form clips from it. Each clip can then be exported to a finished video through the export operation.
What are the rate limits for the BlitzReels API?
The OpenAPI spec does not specify rate limits. Check the provider's site at https://blitzreels.com for current limits before running large clip batches.
Is there a BlitzReels MCP server?
You don't need an MCP server to give your agent the BlitzReels API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent calls it, so you skip installing and syncing a separate server.
Can I limit what my agent is allowed to do with the BlitzReels API?
Yes. Write a rule that allows only the clip create, export, and read operations, so your agent can produce and download clips but cannot empty a media folder or batch-delete projects. Every call it makes is logged.
How do I create and export a clip with the BlitzReels API through Jentic?
Search Jentic for 'create short-form clips' and it returns the create-clips operation with its input schema; the agent passes a source and a preset, then exports each clip through the export operation. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Create AI short-form video clips from a source, apply presets, and export them: preview YouTube sources, manage clips, clip batches, projects, and a workspace media library.
Use for: Create short-form clips from a long video, Preview a YouTube source before clipping, Export a finished clip to video, List the available clip presets
Not supported: Does not host a social account, run paid ads, or stream live video. Use for AI short-form clip creation and export only.
The BlitzReels API creates AI-powered short-form video clips from a source and exports them to finished videos. An agent previews a YouTube source before clipping, generates clips with presets, and exports, promotes, or rejects them after review. It organizes work in clipping projects and a workspace media library, generates caption emoji accents, and tracks clip batches and export jobs across a large management surface.
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.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
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>