Official vendor OpenAPI document · agent-readyMediaVideo Processingbearer8 EndpointsREST
For Agents
Import media into Descript, start audio and video editing jobs, and track them to completion. Reads and deletes jobs by id and fetches published projects by slug.
Use for: Import my video into a Descript project, Start an edit job in Descript, Get the status of a specific job, I want to delete a finished job
Not supported: Does not host or stream finished video, transcribe standalone audio, or manage billing. Use for importing media and running Descript editing jobs only.
The Descript API drives Descript's audio and video editing from code: you import project media, start editing jobs, and track them to completion. You submit an edit-in-Descript job and read back its schema, kick off an agent job that edits a project, list jobs, and read or delete a single job by its id. A published-projects endpoint returns a finished project by slug, and a status endpoint reports service health, so an integration can run a full import-edit-retrieve loop.
Install Jentic One Beta
Connect the Descript API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Descript 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%2Fdescriptapi.com%2Fdescriptapi" | 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%2Fdescriptapi.com%2Fdescriptapi" | 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 Descript API.
Submit an edit-in-Descript job and read back its schema
Import project media into a Descript project
Start an agent job that edits a project programmatically
List editing jobs and read or delete a single job by its id
Fetch a published project by its slug
Check the service status
Use Cases
Patterns agents use Descript API for, with concrete tasks.
★ Agent-Driven Video Editing Pipeline
An AI agent turns raw footage into an edited Descript project by importing the project media, starting an agent job that applies the edits, and polling the job until it finishes. Because jobs are addressable by id, the agent can check progress and react when the edit completes, so a content pipeline runs without a person in the editor.
Import project media, start an agent edit job, and poll the job by id until it reports complete
Published Project Retrieval
Fetch a finished Descript project by its published slug so a downstream app can embed or distribute it. This lets a publishing workflow pull the completed output once editing is done rather than tracking files by hand.
Retrieve a published project by its slug and return its output details
Job Lifecycle Management
Keep an editing queue tidy by listing jobs, reading the state of a specific job, and deleting jobs once their output has been collected. This gives an automation clear control over the editing backlog it created.
List all jobs, read the status of each, and delete the ones that have already been retrieved
Key Endpoints
8 endpoints — the descript api drives descript's audio and video editing from code: you import project media, start editing jobs, and track them to completion.
METHOD
PATH
DESCRIPTION
POST
/edit_in_descript/schema
Submit an edit-in-Descript job and read its schema
POST
/jobs/import/project_media
Import project media
POST
/jobs/agent
Start an agent edit job
GET
/jobs
List editing jobs
GET
/jobs/{job_id}
Read a job by id
DELETE
/jobs/{job_id}
Delete a job by id
GET
/published_projects/{publishedProjectSlug}
Fetch a published project by slug
GET
/status
Service status
POST
/edit_in_descript/schema
Submit an edit-in-Descript job and read its schema
POST
/jobs/import/project_media
Import project media
POST
/jobs/agent
Start an agent edit job
GET
/jobs
List editing jobs
GET
/jobs/{job_id}
Read a job by id
DELETE
/jobs/{job_id}
Delete a job by id
GET
/published_projects/{publishedProjectSlug}
Fetch a published project by slug
GET
/status
Service status
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.
D
Descript API
- AI-Ready (A-)76/100
93
Foundational Compliance77
Developer Experience & Jentic Compatibility64
AI-Readiness & Agent Experience94
Agent Usability60
Security80
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.2
Show dimension breakdown
93
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: A+Signals: 4
98%
Lint Results
Aggregated quality score from linter diagnostics, weighted by severity.
100%
Resolution Completeness
Percentage of `$ref` references that resolve successfully.
100%
Specification Validity
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
75%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
77
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: A-Signals: 4
60%
Example Density
How richly the API is illustrated with examples.
100%
Example Validity
Percentage of examples that conform to their schemas.
50%
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.
64
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: BSignals: 4
68%
Description Coverage
Coverage of descriptions across API elements.
0%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
100%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
87%
Summary Coverage
Coverage of summaries across operations/tags/info.
94
Agent Usability
Functional utility, complexity comfort, and AI orchestration readiness.
Grade: A+Signals: 1
94%
Complexity Comfort
Agent comfort level based on API operational and structural complexity.
60
Security
Trust, risk posture, and security compliance.
Grade: B-Signals: 1
60%
Authentication Strength
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
80
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: A-Signals: 1
80%
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
By hand you provision a bearer token, set the Authorization header, learn the job model across the edit, import, and agent endpoints, and build your own polling loop before an edit completes. Through Jentic you connect once from the API Directory and your agent calls the operations by intent.
Permission scoping
There are eight operations, so you decide exactly which your agent may call, such as importing media and reading jobs while withholding delete. The job id travels in the URL path, so a rule can bind the agent to specific job operations.
Credential isolation
Your bearer token is stored encrypted on your own Jentic One instance and injected into the Authorization header at execution time, never placed in the agent's prompt, logs, or context. You rotate or revoke it in one place.
Intent-based discovery
Agents search Jentic by intent such as 'start an edit job' or 'import project media', and Jentic returns the matching Descript operation with its input schema so the agent calls the right endpoint without reading the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using Descript API through Jentic.
What authentication does the Descript API use?
It uses an HTTP bearer token: every operation requires a bearer credential in the Authorization header. Through Jentic, your own Jentic One instance stores that token encrypted and attaches it to each request rather than exposing it to the agent.
Can I edit a video programmatically with the Descript API?
Yes. You import the project media, then start an agent job that applies the edits, and track the job by its id until it completes. The edit-in-Descript endpoint also returns a schema describing the edit so an integration knows what to send.
What are the rate limits for the Descript API?
The OpenAPI spec does not state rate limits. Check the official Descript API documentation at https://docs.descriptapi.com/ for current limits before submitting many jobs at once.
How do I automate Descript editing through Jentic?
Add the Descript API from the Jentic API Directory and connect your bearer token once. Your agent then searches by intent such as 'start an edit job' and calls the matching operation. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I control which Descript operations my agent is allowed to call?
Yes. There are eight operations, so you grant your agent only the ones it needs, such as importing media and reading jobs while withholding delete. The job id sits in the URL path, so a rule can also pin the agent to specific job operations, and every call is logged.
Is there a Descript API MCP server?
You don't need an MCP server to use the Descript API with your agent. Jentic connects it directly from the API Directory: import it, connect your token once, and your agent can import media and run editing jobs without another server loading tool definitions into its context.
GET STARTED