Skip to content
Descript logo

Connectors / Design and creative · HTTP Connector

Automate Descript with Tray.ai

Import media from a URL, run an AI edit and publish project media in Descript, and start a workflow when Descript sends “Job completed”.

What can you do with Descript on Tray.ai?

Descript is a video and podcast editor where you edit recordings by editing their transcript, with AI edits for captions, filler words, and audio cleanup. Tray.ai connects to Descript through the HTTP Connector, so your workflows can call the Descript API alongside the rest of your stack.

  • When Descript sends “Job completed”, notify the editing team in your team chat.
  • Open a ticket for the video team when Descript sends “Job failed”.
  • Import media from a URL when a new recording lands in your file storage.
  • Export a project transcript and add it to your podcast's show notes in your content system.
Connects through
HTTP Connector
Authentication
A bearer token
Base URL
https://descriptapi.com/v1

Set it up

Connect Descript to Tray.ai

Each step uses Descript's own API details, from its documentation.

Step 1

Save Descript's API token

Save the token Descript issues as a Tray.ai authentication. The HTTP Client sends it as a bearer token on every call. The token stays out of the workflow and out of the logs.

Step 2

Point the HTTP Client at the API

Add an HTTP Client step and use https://descriptapi.com/v1 as the base URL. Or paste a cURL example from Descript's API docs, and Tray.ai fills in the method, URL, and headers.

Step 3

Start with “List agent models”

It's one of 13 documented actions, under Agent edits. The response comes back as data the next step can map into your other apps.

Step 4

Start workflows from Descript events

Give Descript the URL of a Tray.ai webhook trigger. “Job completed” can then start a workflow, and so can 1 other event.

Give your AI agents Descript tools

Build an MCP server on Descript in Agent Gateway and choose which actions your agents can call. Every call runs with access control and an audit trail. How Agent Gateway works

  • Import media from a URL
  • Run an AI edit
  • List projects
  • List jobs
  • Search a drive
  • Import media into a project
  • List agent models
  • Get project details

What the Descript API covers

5 resources and 13 documented actions, each one a call the HTTP Connector can make from a Tray.ai workflow. Connecting it takes a few clicks: here's how.

Media imports

  • Import media from a URL
  • Import media into a project

Agent edits

  • Run an AI edit
  • List agent models

Projects

  • List projects
  • Get project details
  • Publish project media
  • Export a project transcript

Jobs

  • List jobs
  • Get job status
  • Cancel a job

Drive search

  • Search a drive
  • Get published project metadata

Events Descript can send to a Tray.ai webhook trigger

  • Job completed
  • Job failed

Checked against Descript's own documentation on 2026-10-22

help.descript.com/api-and-mcp/api

Frequently asked questions

What can a Tray.ai workflow do in Descript?

+

The Descript API documents 13 actions across 5 resources (Media imports, Agent edits, Projects, Jobs, Drive search). For example: Import media from a URL; Run an AI edit; List projects. A workflow can make any documented call through the HTTP Connector.

How does Tray.ai authenticate with Descript?

+

The Descript API uses a bearer token. You save it once as a Tray.ai authentication, and the HTTP Connector adds it to every request.

Which Descript events can start a Tray.ai workflow?

+

Descript sends 2 events to a webhook URL, for example: Job completed; Job failed. A Tray.ai webhook trigger receives them and starts a workflow.

See Descript working against your stack.

We'll walk through a tailored demo with your systems plugged in.

Great — a couple more details

This helps us connect you with the right person. Optional, and you can skip it.