This MCP connector provides AI-powered speech and audio capabilities via the Brainiall Speech AI APIs. It exposes four core tools allowing an agent to assess pronunciation accuracy, transcribe speech audio into text, synthesize text into natural-sounding speech, and list available voices. Use this connector when your workflow requires integrating voice synthesis, speech recognition, or language learning features. Each tool accepts structured parameters such as base64-encoded audio, target language, and speech speed to give the agent precise control over audio processing.