Unified Codex + Claude tutorial · media

How to add or replace audio in a video with Medux MCP

Learn to add or replace audio in a video with the Medux API through Codex or Claude MCP. Check inputs, tool calls, task status, and output.

POST/api/app/v1/process/video/add_audio_to_video

Replace or add an audio track to a video.

Open the Add Audio to Video API reference →
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 Add or Replace Audio in Video as a Codex MCP task

Use the active workspace as the source of truth. Ask Codex to identify the source video, audio file, and timing requirements, select medux_add_audio_to_video, 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 medux_add_audio_to_video through Medux MCP to add or replace audio in a video.
First inspect and identify the source video, audio file, and timing requirements.
Show me the exact tool arguments before execution.
After the task completes, return the updated video and verify that the new audio is present at the intended time 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 updated video. The final check is explicit: confirm that the new audio is present at the intended time and the full video plays correctly.

What this tutorial does

Medux operation

Replace or add an audio track to a video.

Agent workflow

Codex selects medux_add_audio_to_video, presents the arguments for review, calls Medux, and reports the response.

Before you start

Authentication

  • Authentication is required via Authorization header.

Preconditions

  • Upload the source file and create a file reference before calling this endpoint.
  • Successful requests return a Medux task record immediately. Use the task query or sync endpoints to track completion.
  • All file inputs must be uploaded and persisted as file references before submission.

Prompt Codex

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

Replace or add an audio track to a video.

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
video_file_idstringRequiredInput video file id.
audio_file_idstringRequiredInput audio file id.
model_idstringOptionalModel Default: add-audio-to-video-default.
titlestringOptionalOptional task title.

Step-by-step workflow

01

Connect Medux MCP to Codex

Add the Medux remote MCP endpoint to Codex, provide an authorized credential, and confirm that the medux_add_audio_to_video 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 Codex to run Add Audio to Video

Use one direct instruction with the intended values. Codex 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_add_audio_to_video 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
  ↓
Codex selects medux_add_audio_to_video
  ↓
Review inputs and approve the tool call
  ↓
Medux runs Add Audio to Video
  ↓
Codex reports the response and output

Frequently asked questions

Can Codex use the Medux Add Audio to Video API through MCP?

Codex can call the medux_add_audio_to_video Medux MCP tool to replace or add an audio track to a 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_add_audio_to_video. Review its arguments before approval and consult the API reference for the current contract.

Claude-specific workflow

Run Add an Audio Track to Video as a Claude MCP workflow

Keep the goal, source assets, and constraints together in the conversation. Ask Claude to restate the source video, audio track, and timing requirements before proposing medux_add_audio_to_video. 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 add an audio track to a video with Medux MCP.
Restate which input fulfills each role: the source video, audio track, and timing requirements.
Propose the medux_add_audio_to_video call and summarize its arguments before asking for approval.
When it finishes, return the finished MP4 with a checklist confirming that the new audio starts at the intended time and the video duration is correct.

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 finished MP4 plus a concise validation checklist confirming that the new audio starts at the intended time and the video duration is correct.

Before you start

Source video

A video file without an audio track, such as sample-video-no-audio.mp4.

Audio file

The audio you want to attach, such as sample-audio.m4a.

Requirement: connect the Medux MCP server in Claude before starting. Claude should show the Medux connector in the project context.

Step-by-step workflow

01

Describe the task in one prompt

Tell Claude which audio file and silent video to use, and ask it to upload both files with curl before calling Medux.

Using Medux, add sample-audio.m4a to
sample-video-no-audio.mp4.
Upload both files with the curl command.
Claude prompt for adding audio to a video
A clear prompt gives Claude the media files and the expected workflow.
02

Let Claude request upload URLs

Claude uses the Medux integration to create upload slots for the audio and video. Each slot returns a file ID and a temporary signed upload URL.

Keep the returned file IDs. Medux uses them in the merge request.

03

Upload the audio and video with curl

Run the generated commands in your local terminal. Use the correct content type for each file. The long signed URL is represented below by a placeholder so the command stays readable.

curl -X PUT   -H "Content-Type: audio/mp4"   --data-binary @./sample-audio.m4a   "<SIGNED_AUDIO_UPLOAD_URL>"

curl -X PUT   -H "Content-Type: video/mp4"   --data-binary @./sample-video-no-audio.mp4   "<SIGNED_VIDEO_UPLOAD_URL>"
A successful upload normally returns HTTP 200 with an empty response body.
Claude displays curl commands for uploading audio and video
Claude provides separate upload commands for the audio and video files.
04

Call the Medux audio-to-video tool

After both uploads succeed, Claude calls medux_add_audio_to_video with the audio file ID and video file ID. Medux creates a new processing task.

Tool: medux_add_audio_to_video
Inputs:
  audio_file_id: <AUDIO_FILE_ID>
  video_file_id: <VIDEO_FILE_ID>
Claude calls the Medux add audio to video tool
Claude starts the Medux processing task after both source files are available.
05

Poll the task and download the result

Claude checks the Medux task until it is complete. When the result URL is ready, it downloads the finished video into the project folder.

Tool: medux_task_query
Input:
  task_id: <TASK_ID>

curl -L "<RESULT_DOWNLOAD_URL>"   -o ./sample-video-with-audio.mp4
Claude polls the Medux task
The task is queued and checked until processing finishes.
Claude downloads the finished video
Once complete, Claude downloads the final MP4.

Workflow at a glance

Prompt Claude
Create upload slots
Upload both files
Run Medux task
Download output

Why this workflow is useful

Claude handles the orchestration while Medux handles the media processing. You stay in one conversational workflow instead of building a custom upload interface, writing a separate API client, or switching between multiple dashboards.

Claude plans. MCP connects. Medux processes.

Quick answer

How do I add or replace audio in a video with Medux MCP?

Connect either Codex or Claude to Medux MCP, prepare the required inputs, review the proposed medux_add_audio_to_video 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 add or replace audio in a video

This tutorial addresses developer workflows for add audio to video API and replace audio in a video 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 also fits a broader AI lip sync and talking-avatar pipeline: prepare an approved voice or avatar asset, run audio-to-video lip sync, then verify timing, mouth motion, and final playback.

Can Codex or Claude add or replace audio in 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

Use an auditable audio workflow to add or replace audio in a video

This AI audio processing API workflow lets Codex or Claude add or replace audio in a video while keeping file roles, tool arguments, task IDs, and output checks visible. Use authorized source audio and preserve an input-to-output record when the result feeds voice, dubbing, lip sync, or production video.

A security-conscious audio workflow keeps API keys outside prompts, limits uploaded media to what the task needs, and restricts result access in the calling application. Those operational controls complement the Medux tool call.

How do I make an AI audio workflow easier to audit?

Keep the source asset ID, approved parameters, Medux task ID, returned result, and final listening check together with the project that requested the edit.