# Audexum [Health: Active]

**Category:** 🎙️ Speech-to-Text  
**Repository:** https://audexum.com/integrations/mcp  
**Views:** 2  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/audexum

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

## Claude Desktop Quick Installation
Remote MCP endpoint (confidence: medium). Install path inferred — verify against the README before running it. Add as a URL/SSE server in your client:

```json
"mcpServers": {
  "audexum": {
    "url": "https://audexum.com/integrations/mcp"
  }
}
```

## Documentation

## What Audexum MCP server does

The Audexum MCP server provides two related media capabilities for AI model workflows: text-to-speech generation and transcription. Text-to-speech output is described as MP3 voiceovers, while transcription covers audio and YouTube content converted to text.

This makes the Audexum MCP server relevant when an agent needs to create spoken output from text, or when it needs to work with information contained in recorded speech. For example, an application could use the text-to-speech capability for a voiceover workflow, or use transcription to make audio and YouTube material available as text for an AI model.

It describes the service at the capability level rather than specifying a fixed model provider or media-processing pipeline.

## Tools and capabilities

The documented capabilities are:

- Text-to-speech generation for MP3 voiceovers.
- Transcription of audio content into text.
- Transcription of YouTube content into text.
- Use with AI models.

The Audexum MCP server may fit applications that need both sides of an audio workflow: producing an audio rendition from text and extracting text from existing spoken-media sources.

Because the listing is categorized as Text-to-Speech, generated speech is the clearest stated use case. Transcription is also explicitly included, extending the server beyond speech generation to media-to-text workflows.

## Limitations and notes

It does not provide installation commands, configuration fields, environment variables, authentication instructions, transport details, example requests, or client-specific setup guidance. Developers should verify those details in Audexum’s integration documentation before implementation.

No claims can be made here about supported voices, languages, file formats beyond the stated MP3 voiceover output, YouTube URL requirements, transcript quality, usage limits, pricing, privacy handling, or whether processing occurs locally or remotely. The Audexum MCP server should therefore be evaluated against those requirements separately if they matter to the application.

The description also does not name compatible MCP clients.

_Full upstream README: https://allmcps.com/mcp/audexum/readme_