Mux · Arazzo Workflow

Mux AI Summarize Asset

Version 1.0.0

Create an asset, wait until ready, queue an AI summarize job against it, then poll the job until it completes.

1 workflow 2 source APIs 1 provider
View Spec View on GitHub Video InfrastructureVideo StreamingLive StreamingVideo AnalyticsVideo AIEncodingArazzoWorkflows

Provider

mux-com

Workflows

ai-summarize-asset
Create a ready asset, queue an AI summarize job, and wait for it to complete.
Creates an asset, waits for ready, queues a summarize job, and polls the job until completed.
4 steps inputs: inputUrl, tone outputs: assetId, jobId, status, summaryOutputs
1
createAsset
Create a new asset from the source URL to summarize once it is ready.
2
waitForReady
Poll the asset until its status reaches ready so it can be summarized.
3
queueSummarizeJob
Queue an AI summarize job that targets the ready asset with the chosen tone.
4
waitForJob
Poll the summarize job until its status reaches completed so the generated title, description, and tags can be read.

Source API Descriptions

Arazzo Workflow Specification

Raw ↑
arazzo: 1.0.1
info:
  title: Mux AI Summarize Asset
  summary: Create an asset, wait until ready, queue an AI summarize job against it, then poll the job until it completes.
  description: >-
    Uses Mux Video AI to generate a title, description, and tags for a piece of
    content. The workflow creates an asset from a source URL, waits for the asset
    to reach ready, queues a summarize job targeting that asset with a chosen
    tone, and then polls the job until its status reaches completed so the
    generated outputs can be read. Every step spells out its request inline so
    the flow can be read and executed without opening the underlying OpenAPI
    description.
  version: 1.0.0
  x-realizes-capability-ids:
  - BC-3710
  x-capability-derivation:
    method: 'deterministic join: sourceDescriptions -> per-tag OpenAPI -> tag/capability edge. No classification at this step.'
    min_confidence: 0.7
    sources:
    - capability_id: BC-3710
      capability_name: Media Asset Management
      spec: mux-com-assets-api-openapi.yml
      confidence: 0.9
    model: Turbo EA Capabilities by Vincent Verdet — Turbo EA, https://github.com/vincentmakes/turbo-ea-capabilities, CC BY 4.0
sourceDescriptions:
- name: assetsApi
  url: ../openapi/mux-com-assets-api-openapi.yml
  type: openapi
- name: summarizeApi
  url: ../openapi/mux-com-summarize-api-openapi.yml
  type: openapi
workflows:
- workflowId: ai-summarize-asset
  summary: Create a ready asset, queue an AI summarize job, and wait for it to complete.
  description: >-
    Creates an asset, waits for ready, queues a summarize job, and polls the job
    until completed.
  inputs:
    type: object
    required:
    - inputUrl
    properties:
      inputUrl:
        type: string
        description: A publicly accessible URL to the source video file Mux should ingest.
      tone:
        type: string
        description: Tone for the generated summary (neutral, playful, or professional).
        default: neutral
  steps:
  - stepId: createAsset
    description: >-
      Create a new asset from the source URL to summarize once it is ready.
    operationId: createAsset
    requestBody:
      contentType: application/json
      payload:
        inputs:
        - url: $inputs.inputUrl
        playback_policies:
        - public
    successCriteria:
    - condition: $statusCode == 201
    outputs:
      assetId: $response.body#/data/id
  - stepId: waitForReady
    description: >-
      Poll the asset until its status reaches ready so it can be summarized.
    operationId: getAsset
    parameters:
    - name: ASSET_ID
      in: path
      value: $steps.createAsset.outputs.assetId
    successCriteria:
    - condition: $statusCode == 200
    - context: $response.body
      condition: $.data.status == "ready"
      type: jsonpath
    retryAfter: 5
    retryLimit: 60
    outputs:
      assetId: $response.body#/data/id
  - stepId: queueSummarizeJob
    description: >-
      Queue an AI summarize job that targets the ready asset with the chosen
      tone.
    operationId: create-summarize-job
    requestBody:
      contentType: application/json
      payload:
        parameters:
          asset_id: $steps.waitForReady.outputs.assetId
          tone: $inputs.tone
    successCriteria:
    - condition: $statusCode == 202
    outputs:
      jobId: $response.body#/data/id
      jobStatus: $response.body#/data/status
  - stepId: waitForJob
    description: >-
      Poll the summarize job until its status reaches completed so the generated
      title, description, and tags can be read.
    operationId: get-summarize-job
    parameters:
    - name: JOB_ID
      in: path
      value: $steps.queueSummarizeJob.outputs.jobId
    successCriteria:
    - condition: $statusCode == 200
    - context: $response.body
      condition: $.data.status == "completed"
      type: jsonpath
    retryAfter: 5
    retryLimit: 60
    outputs:
      jobId: $response.body#/data/id
      status: $response.body#/data/status
      outputs: $response.body#/data/outputs
  outputs:
    assetId: $steps.waitForReady.outputs.assetId
    jobId: $steps.waitForJob.outputs.jobId
    status: $steps.waitForJob.outputs.status
    summaryOutputs: $steps.waitForJob.outputs.outputs

Work with this as data

Every workflow here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for arazzo workflows

4 MCP tools reach this
  • find_arazzoBrowse and filter every workflow in the catalog.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This workflow
curl "https://apis.io/api/v1/arazzo/mux-com-ai-summarize-asset-workflow"
All arazzo workflows
curl "https://apis.io/api/v1/arazzo?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.