MXPROCESS

Asynchronous API: AI SOP Documentation Pack

Upload one narrated process demonstration. FFmpeg extracts compact speech audio and four review stills; OpenAI transcribes the narration and creates a reviewable standard operating procedure, execution checklist, controls and exceptions register.

Endpoint: POST https://mxprocess.com/api/files/start-process
Authentication: Bearer JWT from POST /api/login_check
Cost: 26 tokens, charged only by the established successful-action lifecycle.

Start the action

curl --location --request POST 'https://mxprocess.com/api/files/start-process' \
--header 'Authorization: Bearer YOUR_TOKEN' \
--form 'file=@"/path/to/supplier-onboarding-demo.mp4"' \
--form 'actionName="VideoSopDocumentationPack"' \
--form 'parameters=[["language",["English"]],["processName",["Supplier onboarding"]],["audience",["Operations coordinators"]]]' \
--form 'async=true'

Upload exactly one MP4, MOV, MKV, WebM, AVI or M4V up to 1 GB with an audio track. Store id then poll /api/actions/get-action-infos/{id}.

{"id":123,"action":{"actionName":"VideoSopDocumentationPack","slug":"ai-sop-documentation-pack"},"accomplished":false,"trackingUrl":"https://mxprocess.com/api/actions/get-action-infos/123"}

Completed actionResults contains transcript TXT, SOP Markdown, execution-checklist CSV, quality-control CSV, four evidence JPGs and SOP JSON. Download every artifact, including JSON, through /api/actions/download-action-result/123/FILENAME.

Functional error example

{"error":"ERROR_VSDP006 AI SOP Documentation Pack requires a video with an audio track."}

For a client that can wait, use the synchronous API.