Audexum

com.audexumv1.0.1Updated Oct 4, 2026

Text to speech and transcription for any AI model: MP3 voiceovers, audio and YouTube to text.

VerifiedStreamable HTTPWeb executableMedia & Design

Overview

AI-generated overview

Audexum lets an assistant generate MP3 voiceovers from text and transcribe audio or YouTube content into text.

What it does
Audexum is a remote text-to-speech and transcription service exposed over MCP. According to its description, it turns text into MP3 voiceovers and converts audio or YouTube sources into text. It is meant to work with any AI model, so an assistant can request speech output or a transcript as part of a workflow.
When to use it
Worth adding when you want an assistant to produce spoken audio from written content, or to turn recordings or YouTube videos into text you can search, summarize, or reuse. It is a fit for voiceover and transcription tasks rather than general file or document handling.
Requirements
It runs as a remote endpoint at audexum.com over streamable HTTP, so network access is needed. The manifest declares no authentication, environment variables, headers, or packages, but the provider's integration page should be checked for any account or key requirements.
Before you install
The manifest declares no credentials, but the service is third-party and remote: text you submit for voiceover and audio or YouTube links you submit for transcription are sent to audexum.com. Confirm the provider's terms, retention, and any usage limits or costs before relying on it for private or sensitive content.

Installation

In SourceWeft

  1. Open Audexum in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "audexum": {
      "type": "http",
      "url": "https://audexum.com/mcp"
    }
  }
}

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v1.0.1LatestOct 4, 2026