For Agents
Render personalised videos from Glitterly templates and manage generated video assets through a small CRUD-style API.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Glitterly 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%2Fglitterly.app%2Fglitterly" | 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%2Fglitterly.app%2Fglitterly" | 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 Glitterly API.
Render a personalised video from a saved Glitterly template by passing dynamic field values
List previously generated videos to find one to embed or share
Fetch a single Glitterly video by ID to read its render status and output URL
GET STARTED
Use for: I need to generate a personalised video from a Glitterly template, List all Glitterly templates available to my account, Get the render status of a Glitterly video by ID, Retrieve the output URL of a generated video
Not supported: Does not edit video timelines, transcribe audio, or generate raw clips - use for template-driven personalised video rendering only.
Jentic publishes the only available OpenAPI specification for the Glitterly API, keeping it validated and agent-ready. Glitterly is a programmatic video generation platform: you design a video template once and then render personalised video variants on demand by passing dynamic text, images, and brand assets. The API exposes the two primitives needed to drive that flow - listing reusable templates and creating, listing, fetching, or deleting individual videos.
Delete a Glitterly-generated video that is no longer needed
List the templates available to the authenticated workspace before rendering
Patterns agents use Glitterly API for, with concrete tasks.
★ Personalised Video Outreach
Sales and growth teams can render thousands of personalised cold-outreach videos by storing a single template in Glitterly and calling POST /videos with the recipient's name, company, and offer per request. The API returns a video ID and, once rendering completes, a hosted URL suitable for embedding in an email. Setup is a few hours once the template is designed.
POST /videos with templateId and the dynamic fields {firstName, company}, then GET /videos/{videoId} until status is ready and capture the output URL.
Personalised Onboarding and Lifecycle Video
Lifecycle marketing teams can drop a Glitterly-rendered video into onboarding emails, replacing static screenshots with a short clip that names the user. The same template feeds renewal and re-engagement campaigns by varying the dynamic fields per send. Storage cleanup is straightforward via DELETE /videos/{videoId} once a campaign window closes.
GET /templates to find the onboarding template, POST /videos with the user's name and plan, and store the resulting video URL on the user record.
Agent-Driven Video Asset Generation
An AI agent producing campaign assets through Jentic can render a Glitterly video as one of several output types alongside images and copy. Because the surface is small (5 endpoints), the agent can integrate it with a single Jentic search and a single execute call per render, then poll for completion.
Search Jentic for 'render glitterly video', load the schema for POST /videos, and submit with the per-recipient field values from the campaign brief.
5 endpoints — jentic publishes the only available openapi specification for the glitterly api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
/templates
List available templates
/videos
Render a video from a template
/videos
List generated videos
/videos/{videoId}
Get a single video by ID
/videos/{videoId}
Delete a generated video
/templates
List available templates
/videos
Render a video from a template
/videos
List generated videos
/videos/{videoId}
Get a single video by ID
/videos/{videoId}
Delete a generated video
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Glitterly by hand means learning its X-API-Key header auth and stitching the template lookup and video render endpoints together yourself, against docs gated behind login. Through Jentic you install once, import the Glitterly API from the API Directory, store the key once, and your agent calls it.
Permission scoping
Glitterly takes the render target in the request body and returns a video id in the path, so scope the agent to the operations it needs, such as listing templates and rendering a video. You choose that operation set, so destructive ones like deleting a video are not included unless you add them.
Credential isolation
Your Glitterly 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 'render a personalised video', and Jentic returns the matching Glitterly operation with its input schema so the agent submits the right payload without reading docs gated behind login.
Alternatives and complements available in the Jentic catalogue.
Specific to using Glitterly API through Jentic.
Why is there no official OpenAPI spec for the Glitterly API?
Glitterly does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call the Glitterly API via structured tooling. It is validated against the live API and kept up to date. Get started with Jentic One, the self-hosted execution layer.
What authentication does the Glitterly API use?
Glitterly uses an API key sent in the X-API-Key header. Through Jentic the key is stored in the vault and the header is injected at execution time, so the raw key never enters the agent's context.
Can I render personalised videos through the Glitterly API?
Yes. POST /videos with a templateId and the dynamic field values returns a video ID. Render is asynchronous, so poll GET /videos/{videoId} until the response shows the render is complete and the output URL is populated.
What are the rate limits for the Glitterly API?
Glitterly does not document rate limits in this OpenAPI spec, and its public docs are gated. Render volume is typically governed by your plan rather than a per-second limit; spread bulk renders across a queue rather than sending hundreds of POST /videos calls at once.
How do I list available templates through Jentic?
Search Jentic for 'list glitterly templates', load the schema for GET /templates, and execute it with no parameters. Run pip install jentic to install the SDK.
Can I delete a video after a campaign ends?
Yes. DELETE /videos/{videoId} removes the rendered video. List recent videos via GET /videos to find IDs, then delete in batch as part of a campaign teardown job.
Can I limit what my agent is allowed to do with the Glitterly API?
Yes. Because Jentic One is self-hosted, you decide which Glitterly operations your agent can call, so you can grant listing templates with GET /templates and rendering a video with POST /videos while withholding everything else. Read-only reporting can be limited to GET /videos and GET /videos/{videoId}, and the destructive DELETE /videos/{videoId} operation is only available if you explicitly add it to the agent's allowed set. Your own rules also govern which stored credentials the agent may use at execution time.