English Français العربية

Brainiall MCP Server

Community Media and design

Speech tools: pronunciation assessment with phoneme-level feedback, speech-to-text with language detection and text-to-speech with multiple voices.

Source code Documentation

Install

The installation steps are in the documentation below. Documentation

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. Brainiall Speech AI - MCP Server
  2. Tools
  3. Prerequisites
  4. Installation
  5. Configuration
  6. Running Locally
  7. API Reference
  8. License
  9. Links

Brainiall Speech AI - MCP Server

MCP server providing AI-powered pronunciation assessment, speech-to-text, and text-to-speech tools via Brainiall Speech AI APIs.

Tools

ToolDescription
assess_pronunciationScore how accurately a speaker pronounced a given text (0-100), with per-word and phoneme-level feedback
transcribe_speechTranscribe speech audio into text with automatic language detection
synthesize_speechConvert text to natural-sounding speech audio (MP3)
list_voicesList all available text-to-speech voices

Prerequisites

Get your free API key at app.brainiall.com.

Installation

Using pip
pip install fastmcp httpx
Using Docker
docker build -t brainiall-mcp .
docker run -e BRAINIALL_API_KEY=your-key -p 8000:8000 brainiall-mcp

Configuration

Set the BRAINIALL_API_KEY environment variable:

export BRAINIALL_API_KEY=your-api-key
Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "brainiall-speech-ai": {
      "command": "fastmcp",
      "args": ["run", "server.py"],
      "env": {
        "BRAINIALL_API_KEY": "your-api-key"
      }
    }
  }
}
Cursor / VS Code

Add to your MCP settings:

{
  "mcpServers": {
    "brainiall-speech-ai": {
      "command": "fastmcp",
      "args": ["run", "/path/to/server.py"],
      "env": {
        "BRAINIALL_API_KEY": "your-api-key"
      }
    }
  }
}
Streamable HTTP (Docker / Remote)
docker run -e BRAINIALL_API_KEY=your-key -p 8000:8000 brainiall-mcp

Connect your MCP client to http://localhost:8000/mcp.

Running Locally

# stdio (default for Claude Desktop / Cursor)
BRAINIALL_API_KEY=your-key fastmcp run server.py

# streamable-http
BRAINIALL_API_KEY=your-key fastmcp run server.py --transport streamable-http --port 8000

API Reference

All tools communicate with the Brainiall Speech AI API at https://api.brainiall.com. Full API documentation is available at app.brainiall.com.

assess_pronunciation
ParameterTypeRequiredDescription
textstringYesReference text the user should have read
audio_base64stringYesBase64-encoded audio (WAV or MP3)
languagestringNoLanguage code, default en-US
transcribe_speech
ParameterTypeRequiredDescription
audio_base64stringYesBase64-encoded audio (WAV, MP3, WEBM, OGG)
languagestringNoLanguage hint for transcription
synthesize_speech
ParameterTypeRequiredDescription
textstringYesText to convert to speech
voicestringNoVoice ID, default alloy
speedfloatNoSpeed multiplier (0.5-2.0), default 1.0
list_voices

No parameters. Returns available voice options with IDs and supported languages.

License

MIT

Frequently asked questions

What is Brainiall MCP Server?

Speech tools: pronunciation assessment with phoneme-level feedback, speech-to-text with language detection and text-to-speech with multiple voices.

How do I install Brainiall MCP Server?

Follow the installation steps in its documentation, shown on this page and in its repository.

Is Brainiall MCP Server open source?

Yes. Its code is on GitHub under the MIT license.

Who maintains Brainiall MCP Server?

It is published by fasuizu-br. AI.tn lists it but does not maintain or endorse it.

From the community awesome-mcp-servers lists and the project's GitHub repository. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.