Speech AI Pronunciation, STT & TTS

What Speech AI - Pronunciation, STT & TTS does

Speech AI - Pronunciation, STT & TTS exposes three speech capabilities to MCP-compatible AI coding assistants: English pronunciation assessment, speech-to-text transcription, and text-to-speech generation. Pronunciation results are scored from 0 to 100 at phoneme, word, and sentence levels. Transcription includes word-level timestamps and confidence scores. Speech generation supports 12 English voices spanning American and British variants, with playback speed adjustable from 0.5x to 2.0x.

The package also defines a speech-workflow skill for a complete practice cycle: listen, record, receive a score, and improve. Its pronunciation-tutor agent supports structured interactive practice sessions.

How it works

The integration uses the Model Context Protocol to make speech operations available to an AI assistant. A client sends requests to the hosted MCP endpoint and authenticates them with an Ocp-Apim-Subscription-Key header. The endpoint is:

https://pronunciation-mcp.thankfulfield-a7857897.eastus.azurecontainerapps.io/mcp

Available skills are assess-pronunciation, transcribe-audio, and speech-workflow. The first evaluates recorded audio, the second converts English audio to text with timing and confidence metadata, and the third combines the practice steps into one workflow.

Setup and configuration

Speech AI - Pronunciation, STT & TTS can be installed through Claude Code with /plugin install speech-ai or added in Cursor with /add-plugin speech-ai. Other MCP clients can use the hosted endpoint through their MCP settings.

A manual configuration supplies the endpoint URL and an API key in the request headers:

{
  "mcpServers": {
    "speech-ai": {
      "url": "https://pronunciation-mcp.thankfulfield-a7857897.eastus.azurecontainerapps.io/mcp",
      "headers": {
        "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
      }
    }
  }
}

Obtain an API key from brainiall.com or through Azure Marketplace. No environment variable configuration is specified in the provided installation instructions.

Tools and capabilities

• Assess English pronunciation at phoneme, word, and sentence levels with scores from 0 to 100.
• Transcribe English audio with word-level timestamps and confidence values.
• Generate English speech with 12 American and British voices.
• Adjust generated speech speed between 0.5x and 2.0x.
• Run a structured pronunciation practice loop through the speech-workflow skill.
• Use the pronunciation-tutor agent for guided practice sessions.

Limitations and notes

The documented speech-to-text capability is for English audio, and the documented pronunciation assessment covers English pronunciation. The API is a proprietary commercial service, while the plugin configuration files are licensed under MIT. It also describes sub-300ms transcription latency, but does not define the conditions or measurement method for that figure.