Inspect the matching API task
Compare the request fields and response in Playground, then use API Docs for uploads, authentication, and task status.
Open the matching Playground taskUpload a video you own or are authorized to edit, then describe the visible watermark. Medux identifies the target from your words and processes the clip without a manually drawn region.
Start with 3,000 free trial credits for eligible tasks. Compare free credits and usage limits.
Upload a video you can edit. Describe the mark clearly, including its appearance and position; use sample to see a starting phrase.
The latest task appears below. Processing continues on the server if you leave this page.
Use only media you own or are authorized to edit. Review the processed result before publishing it.
No processed video yet. Generate one to see it here.
Use the service behind this Workshop in your application or AI agent. Explore the API reference and its corresponding MCP tool before starting an integration.
Compare the request fields and response in Playground, then use API Docs for uploads, authentication, and task status.
Open the matching Playground taskConnect an agent to Medux MCP and inspect the available media processing tools.
See the MCP connection guideChoose a clip you own or have permission to clean.
Enter the watermark's appearance or location in the prompt field.
Inspect the edited corner or region across the finished video before downloading.
Remove a draft overlay from a clip you created for review.
Prepare an authorized asset when you have rights to use an unmarked version.
Use the same video file ID and prompt text in a connected workflow.
Mention the mark's text, shape, and position when possible.
Review shots where the background behind the mark becomes more complex.
Only edit video you own or are authorized to modify.
Every Medux tool has open examples on GitHub: copy a prompt for Claude or Codex, or start from a working API request.
A ready-to-paste prompt and approval checklist for running medux_watermark_removal_by_prompt from Claude.
View on GitHubThe same workflow for Codex: expected tool call, arguments to review and how to verify the result.
View on GitHubRequest fields, curl, Python and JavaScript samples, and response handling for this endpoint.
View on GitHubNo. This API accepts input_file_id and required prompt_text. Describe the visible mark instead of selecting a pixel region. Use only footage you have permission to edit.
New Medux users receive 3,000 trial credits for eligible tools. Processing tasks consume credits and plan limits apply. Check Pricing for the current limits and your Account for the final task cost.
Use media you own or are authorized to edit. If a real person appears, make sure your use of the footage and likeness is permitted.
Preview and download the completed result on this page. The submitted task is also available in Account Results.