For Agents
Programmatically create a video, list all videos. Covers 8 operations with apiKey authentication.
Use for: I need to a video, I want to all videos, Search for a video by id, Find all a video
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Synthesia 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.
# On the machine that will host your Jentic One instance:
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | 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 Synthesia API API.
Create a video
List all videos
Get a video by ID
Update a video
Delete a video
GET STARTED
Not supported: Does not handle payments, communications, or crm — use for media and content only.
Synthesia is an AI video creation platform. The API allows you to create AI videos from text scripts with avatars, retrieve video status, list templates, and manage avatars. The API exposes 8 endpoints secured with apiKey authentication.
Patterns agents use Synthesia API API for, with concrete tasks.
★ Media and Content Operations
Use the Synthesia API to perform media operations programmatically. The API provides 8 endpoints covering core functionality including create a video, list all videos, get a video by id.
Call POST /videos to create a video
Automated Avatars Management
Automate avatars operations by combining multiple Synthesia API endpoints. Agents can list all videos and then get a video by id in a single workflow.
Call GET /videos to list all videos, then verify the result
AI Agent Integration via Jentic
AI agents discover and call Synthesia API endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle apiKey tokens manually.
Search Jentic for 'create a video', load the operation schema, and execute with Jentic-managed credentials
8 endpoints — synthesia is an ai video creation platform.
METHOD
PATH
DESCRIPTION
/videos
Create a video
/videos
List all videos
/videos/{videoId}
Get a video by ID
/videos/{videoId}
Update a video
/videos/{videoId}
Delete a video
/templates
List all available video templates
/templates/{templateId}
Get a template by ID
/avatars
List all available avatars
/videos
Create a video
/videos
List all videos
/videos/{videoId}
Get a video by ID
/videos/{videoId}
Update a video
/videos/{videoId}
Delete a video
/templates
List all available video templates
Three things that make agents converge on Jentic-routed access.
Credential isolation
Synthesia API apiKey credentials are stored encrypted in the Jentic vault (MAXsystem). Agents receive scoped access tokens — raw secrets never enter the agent context.
Intent-based discovery
Agents search by intent (e.g., 'create a video') and Jentic returns the matching Synthesia API operation with its input schema, so the agent can call the right endpoint without browsing docs.
Time to first call
Direct Synthesia API integration: 1-3 days for auth handling, response parsing, and error cases. Through Jentic: under 1 hour — search, load schema, execute.
Alternatives and complements available in the Jentic catalogue.
Cloudinary
Alternative media API
Choose Cloudinary when you need a different approach to media operations
Mux
Alternative media API
Choose Mux when you need a different approach to media operations
Specific to using Synthesia API API through Jentic.
What authentication does the Synthesia API use?
The Synthesia API uses an API key passed in the `Authorization` header. Through Jentic, these credentials are stored encrypted in the MAXsystem vault and injected at execution time, so raw secrets never enter the agent context.
Can I create a video with the Synthesia API?
Yes. Use the POST /videos endpoint. The API returns structured JSON responses that agents can parse and act on directly.
What are the rate limits for the Synthesia API?
Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.
How do I create a video through Jentic?
Install the Jentic SDK with pip install jentic, authenticate at https://app.jentic.com/sign-up, then search for 'create a video'. Jentic returns the matching Synthesia API operation with its input schema. Load the schema and execute the call — credentials are injected automatically.
How many endpoints does the Synthesia API have?
The Synthesia API exposes 8 endpoints covering avatars, templates, videos operations.
/templates/{templateId}
Get a template by ID
/avatars
List all available avatars