Unified Codex + Claude tutorial · process

How to remove subtitles from a video with Medux MCP

Learn to remove subtitles from a video with the Medux API through Codex or Claude MCP. Check inputs, tool calls, task status, and output.

Watch the complete workflow: remove subtitles from a video with Codex, Claude, MCP, and Medux. Watch on YouTube ↗
Choose your AI client

Follow the Codex or Claude workflow

The Medux operation and request fields are shared. Switch tabs for the client-specific prompt, approval pattern, screenshots, and walkthrough.

Codex-specific workflow

Run Remove Subtitles from Video as a Codex MCP task

Use the active workspace as the source of truth. Ask Codex to identify the source video and any subtitle region or processing options, select the Medux subtitle-removal tool, and keep the Medux task ID and returned output with the rest of the project. Naming the input roles and the expected result prevents an agent from guessing which file should be used where.

Codex prompt pattern

In this workspace, use the Medux subtitle-removal tool through Medux MCP to remove subtitles from a video.
First inspect and identify the source video and any subtitle region or processing options.
Show me the exact tool arguments before execution.
After the task completes, return the subtitle-free video and verify that the visible subtitles are removed through the required frames and the full video plays correctly.

Approval gate

Before approving the call, compare the selected tool, file or asset IDs, ordering, timing, and output settings with the request. If a local filename was mapped to an uploaded Medux file ID, keep that mapping visible so it can be audited later.

Result verification

Let Codex monitor an asynchronous task until it reaches a terminal state, then save or report the subtitle-free video. The final check is explicit: confirm that the visible subtitles are removed through the required frames and the full video plays correctly.

Workflow overview

The video tutorial shows a compact agent workflow: prepare the file, give Codex the task, upload the asset to Medux, start subtitle removal, poll the task, then download and preview the result.

Prepare video
Prompt Codex
Upload to Medux
Run removal
Download MP4

Before you start

Codex projectUse a workspace where your source video can be read from a local path.
Medux MCP accessMake sure the Medux MCP server is already configured and available to Codex.
Source videoIn the recording, the input is named remove_subtitle.mp4.
Approval flowWhen Codex asks to call a Medux MCP tool, approve the action and let it continue.

Step-by-step tutorial

01

Put the source video in your Codex workspace

Open the project that already has the Medux MCP server connected. Place the video you want to clean in the workspace so Codex can access it directly.

/Users/chuan/projects/test_mudex/remove_subtitle.mp4
Codex workspace with the subtitle removal request
The tutorial starts with one local MP4 file and a simple Codex request.
02

Ask Codex to remove the visible subtitles

Keep the instruction direct. Tell Codex which file to use, what result you want, and that it should call Medux through MCP instead of doing unnecessary local analysis.

Remove all visible subtitles from the video located at /Users/chuan/projects/test_mudex/remove_subtitle.mp4 and output a clean version without subtitles. Use Medux. Call the Medux MCP directly and do not perform excessive analysis.
03

Let Codex request a Medux upload URL

Codex asks Medux for an upload target, then sends the local MP4 to that signed URL. In the recorded flow, Codex also keeps the upload request precise by using the returned content type.

curl --path-as-is -X PUT -T ./remove_subtitle.mp4   -H "Content-Type: video/mp4"   "<medux_signed_upload_url>"
Codex requesting a Medux upload URL
Codex creates the upload step and prepares to push the local MP4 to Medux.
04

Start the Medux subtitle-removal task

After the upload succeeds, Codex calls the Medux processing workflow. Medux handles the actual subtitle removal in the cloud, while Codex keeps the job organized inside the same chat.

Medux MCP action:
- input: uploaded MP4 asset
- task: remove visible subtitles
- output: cleaned MP4
Codex starting Medux subtitle removal
Once the upload is accepted, Codex starts the Medux subtitle-removal task.
05

Approve the MCP tool call and wait for processing

When Codex needs permission to query the Medux task, approve the MCP call. Codex then checks the task status at intervals until Medux returns the final output URL.

Medux task status:
PROCESSING → PROCESSING → COMPLETED
Codex asking for approval to query the Medux task
Approve the Medux task query inside Codex.
Codex polling Medux task status
Codex continues polling instead of restarting the task.
06

Download and preview the clean video

When the task completes, Codex downloads the cleaned MP4 back into the workspace. Open the result and preview it to confirm that the visible subtitles are gone.

clean output:
/Users/chuan/projects/test_mudex/remove_subtitle_clean.mp4
Codex downloading the completed Medux output
Codex downloads the completed Medux result.
Final cleaned video preview without subtitles
The final MP4 is ready to publish or reuse.

Publishing checklist

Before you post the tutorial on your site, docs, blog, or social channels, keep the story focused on the agent workflow: Codex gives instructions, Medux processes the video, and the final clean asset returns to the workspace.

Use one clear input path and one clear output name.
Keep command snippets wrapped so they never overflow on mobile.
Preview the final MP4 before sharing or reusing it.

Example result

Subtitle removal result

Play the final video below to review the subtitle-removal result generated by Medux.

Generated result. Final video after visible subtitles were removed by Medux.

Claude-specific workflow

Run Remove Subtitles from Video as a Claude MCP workflow

Keep the goal, source assets, and constraints together in the conversation. Ask Claude to restate the source video and any subtitle region or processing options before proposing medux_video_remove_subtitle. That context checkpoint makes the file roles and desired outcome easy to correct before any Medux call is approved.

Claude prompt pattern

Using the assets and requirements in this conversation, help me remove subtitles from a video with Medux MCP.
Restate which input fulfills each role: the source video and any subtitle region or processing options.
Propose the medux_video_remove_subtitle call and summarize its arguments before asking for approval.
When it finishes, return the subtitle-free video with a checklist confirming that the visible subtitles are removed through the required frames and the full video plays correctly.

Context checkpoint

Have Claude summarize the intended transformation, identify every source asset by role, and list the important constraints. Review that summary together with the proposed tool arguments; correct the conversation first if a file, order, time range, or setting is ambiguous.

Result verification

Keep the Medux task ID in the conversation while Claude checks progress. When processing ends, ask for the subtitle-free video plus a concise validation checklist confirming that the visible subtitles are removed through the required frames and the full video plays correctly.

What this tutorial does

Medux operation

Create a video processing task that removes subtitles from an uploaded video.

Agent workflow

Claude selects medux_video_remove_subtitle, presents the arguments for review, calls Medux, and reports the response.

Before you start

Authentication

  • Authentication is required via Authorization header.

Preconditions

  • Requires a previously uploaded video asset.
  • Requires an existing video file id.

Prompt Claude

Start with a clear instruction that names the Medux operation and the intended inputs.

Remove burned-in subtitles from the uploaded source video {file id}. If the subtitle area is known, pass region {x, y, width, height}.

Request fields to review

Confirm these values before approving the MCP tool call. The linked API page remains the source of truth for current limits and response semantics.

FieldTypeRequirementPurpose
file_idstringRequiredProvide the value described in the API reference.
region.heightint32OptionalProvide the value described in the API reference.
region.widthint32OptionalProvide the value described in the API reference.
region.xint32OptionalX coordinate of the region's top-left corner in pixels.
region.yint32OptionalY coordinate of the region's top-left corner in pixels.
titlestringOptionalProvide the value described in the API reference.

Step-by-step workflow

01

Connect Medux MCP to Claude

Add the Medux remote MCP endpoint to Claude, provide an authorized credential, and confirm that the medux_video_remove_subtitle tool is available.

02

Prepare the required inputs

Prepare the source files, asset IDs, text, or settings required by the operation. Upload local media first when the tool requests file IDs.

03

Ask Claude to run Create Video Subtitle Removal

Use one direct instruction with the intended values. Claude should select the Medux tool and show the proposed arguments before execution.

04

Review and approve the tool call

Check that the tool is medux_video_remove_subtitle and that each file ID, task ID, option, and output setting matches your request before approving it.

05

Check the Medux response

If Medux returns an asynchronous task, let the agent monitor it until completion; otherwise review the immediate response and save any result identifiers or output URLs.

Workflow recap

User goal
  ↓
Claude selects medux_video_remove_subtitle
  ↓
Review inputs and approve the tool call
  ↓
Medux runs Create Video Subtitle Removal
  ↓
Claude reports the response and output

Frequently asked questions

Can Claude use the Medux Create Video Subtitle Removal API through MCP?

Claude can call the medux_video_remove_subtitle Medux MCP tool to create a video processing task that removes subtitles from an uploaded video. This guide covers the required inputs, approval flow, result handling, and the matching API reference.

Which MCP tool does this tutorial use?

This workflow uses medux_video_remove_subtitle. Review its arguments before approval and consult the API reference for the current contract.

Quick answer

How do I remove subtitles from a video with Medux MCP?

Connect either Codex or Claude to Medux MCP, prepare the required inputs, review the proposed medux_video_remove_subtitle call, and verify the returned result. The tabs above keep client-specific prompting on one canonical page.

Can I use the same Medux tool in Codex and Claude?

Yes. The client interaction differs, but both use the same Medux MCP tool and API request contract shown in this tutorial.

Related developer intent

Use AI agents to remove subtitles from a video

This tutorial addresses developer workflows for remove subtitles from video and AI video text remover by making the task repeatable through the Medux API. Codex or Claude can prepare inputs, show the MCP tool arguments for approval, monitor processing, and return an output that can be checked against the original request.

This capability fits a broader AI video editing pipeline alongside video watermark removal, logo removal, object cleanup, resizing, and output validation for owned or authorized media.

Can Codex or Claude remove subtitles from a video through Medux MCP?

Yes. Use the client-specific tab above to prepare the inputs, review the Medux tool call, run the operation, and verify the returned result. The linked API reference remains the source of truth for supported fields and limits.

Production, trust, and developer intent

Apply rights-aware controls when you remove subtitles from a video

Use this as an authorized AI media processing workflow for remove subtitles from a video. Codex or Claude can expose the selected files, tool arguments, task status, and result checks, making the edit easier to review than an opaque one-click video operation.

Only process media you own or are permitted to modify. For production and commercial publishing, retain the source license or authorization, review the changed region, and record who approved the final output.

What should I verify before running an AI video editing API?

Verify ownership or permission, choose the operation that matches the requested edit, inspect the complete output, and keep the task record with the approved source file.