How do I run Create a Text-Driven Avatar Video with Codex MCP?

Codex can use medux_video_create_text_driven through Medux MCP to generate an avatar video from text with reusable avatar and voice assets. The workflow identifies the exact inputs, reviews the tool arguments, monitors processing, and verifies the returned result.

Codex MCP tutorial · generate

How to create a text-driven avatar video with Codex MCP and Medux

Q: Which MCP tool does this tutorial use?

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

Use Codex and Medux through MCP to generate an avatar video from text with reusable avatar and voice assets. This guide covers input preparation, the approval gate, task monitoring, and a concrete output check.

POST/api/app/v1/generate/video/text_driven

Generate an avatar video from text using a reusable avatar and voice.

Open the Create Text Driven Video API reference →

Codex-specific workflow

Run Create a Text-Driven Avatar Video as a Codex MCP task

Use the active workspace as the source of truth. Ask Codex to identify the script, avatar ID, voice ID, and supported video settings, select medux_video_create_text_driven, 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_video_create_text_driven through Medux MCP to create a text-driven avatar video.
First inspect and identify the script, avatar ID, voice ID, and supported video settings.
Show me the exact tool arguments before execution.
After the task completes, return the generated talking-avatar video and verify that the avatar, voice, and spoken script match the request 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 generated talking-avatar video. The final check is explicit: confirm that the avatar, voice, and spoken script match the request and the full video plays correctly.

What this tutorial does

Medux operation

Generate an avatar video from text using a reusable avatar and voice.

Agent workflow

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

Before you start

Authentication

Authentication is required via Authorization header.

Preconditions

Prepare avatar and voice assets before calling this endpoint.
Requires avatar asset id, voice asset id, and non-empty text.
Avatar and voice IDs can come from your Media Assets or official public assets.
Also accepts optional duration seconds, links, clarity, aspect ratio, and model.

Prompt Codex

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

Create a 7 second 1080P 16:9 talking video from this script using avatar asset id {avatar asset id}, voice asset id {voice asset id}, and model id talking-video-text-standard.

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.

Field	Type	Requirement	Purpose
`aspect_ratio`	string	Optional	Requested output aspect ratio, such as 16:9 or 9:16.
`avatar_asset_id`	string	Required	Reusable avatar asset ID owned by the current user or listed as an official public asset.
`clarity`	string	Optional	Requested output resolution label, such as 1080P or 2K.
`duration_seconds`	int32	Optional	Requested output duration, in seconds.
`links`	array<string>	Optional	Optional reference links submitted from the Playground form.
`model`	string	Optional	Generation model label or version selected in the Playground form.
`model_id`	string	Optional	Stable public Medux model identifier.
`text`	string	Optional	Provide the value described in the API reference.
`title`	string	Optional	Provide the value described in the API reference.
`voice_asset_id`	string	Required	Reusable voice asset used for text-driven lip sync.

Step-by-step workflow

Connect Medux MCP to Codex

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

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.

Ask Codex to run Create Text Driven Video

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

Review and approve the tool call

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

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_video_create_text_driven
  ↓
Review inputs and approve the tool call
  ↓
Medux runs Create Text Driven Video
  ↓
Codex reports the response and output

Frequently asked questions

Can Codex use the Medux Create Text Driven Video API through MCP?

Codex can call the medux_video_create_text_driven Medux MCP tool to generate an avatar video from text using a reusable avatar and voice. 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_create_text_driven. Review its arguments before approval and consult the API reference for the current contract.