Workflow Overview: The automation is split into two workflows: the first handles video upload and indexing, and the second checks for profanity and sends the results via Slack DM. This design ensures longer-running indexing tasks complete properly while still delivering actionable insights.
Goals:
Automate detection of profanity or vulgar language in uploaded videos. Split the workflow into two parts to handle longer processing times without Zapier timeouts. Send detected profanity results and timestamps directly to Slack for review. Use target labels to ensure only the intended second workflow is triggered. Prerequisites:
A Zapier account to manage and run workflows. Access to VideoDB with an active API key. A Slack workspace with permissions to send direct messages or channel messages. A Zapier Interface form to collect video name and URL submissions. Basic understanding of asynchronous job handling in Zapier. Detailed Steps:
Workflow 1: Upload and Index Video
Form Creation (Zapier Interfaces): Build a form with fields for Video Name and Video URL. Example: Enter a video title and a YouTube link. Set trigger to Form Submission Created (Zapier Interfaces). Select the created form and page as the source. Upload and Index with VideoDB: Add an action → VideoDB → Upload and Index Video. Authenticate using your VideoDB API key. Map fields: Video Name and URL from form submission. Set prompt: Check for any profanity or vulgar content. Assign a target label (e.g., Profanity Check) to connect with the second workflow. Test → confirm Job ID is returned (asynchronous task). Activate the workflow so all new form submissions trigger video uploads automatically. Workflow 2: Profanity Detection and Slack Notification
Trigger: New Video Uploaded Job Completed (VideoDB). Filter by target label Profanity Check. Find Video Moment (Profanity Check): Action: VideoDB → Find Video Moment. Use dynamic video ID from the trigger. Prompt: Detect profanity or vulgar content. Content type: Multimodal (spoken + visual). This action returns a new Job ID for processing. Insert a delay (e.g., 3 minutes) to allow VideoDB to finish analyzing. Action: VideoDB → Check Job Status. Input the Job ID from the “Find Video Moment” step. Retrieve results: detected profanity, timestamps, and URLs. Action: Slack → Send Channel or DM Message. Configure message format: Profanity results (text + timestamps) Customize bot name (e.g., Profanity Checker). Test → confirm profanity results are delivered in Slack. Activate the workflow to automatically run profanity checks and push results to Slack. Links to workflows:
Automatically Detect Profanity in Videos with AI - Update on Slack