Add Speech AI MCP Server (Pronunciation, TTS, STT)

[fasuizu-br]

MCP Server: Speech AI

Add Speech AI MCP server providing pronunciation assessment, speech-to-text, and text-to-speech capabilities for AI agents.

Tools

Tool	Description
assess_pronunciation	Score English pronunciation at phoneme, word, and sentence levels (0-100)
transcribe_audio	Transcribe audio to text with word-level timestamps
synthesize_speech	Generate speech from text with 12 English voices (US + UK accents)
list_tts_voices	List available TTS voices

Key Features

• 17MB model, <300ms latency for pronunciation assessment
• Phoneme-level scoring with IPA notation
• 12 English voices (US + UK accents) for TTS, ranked Wanted: who's using Higress 欢迎分享使用经验、提出产品诉求。 #1 on TTS Arena
• Word-level timestamps for STT
• Production-ready, deployed on Azure with 100% uptime

API Details

• Base URL: https://apim-ai-apis.azure-api.net
• Auth: Ocp-Apim-Subscription-Key header
• Formats: WAV, MP3, OGG, FLAC, WebM
• Pricing: $0.02/call (free tier available via Azure Marketplace)

Links

• Website: https://brainiall.com
• GitHub Examples: https://github.com/fasuizu-br/speech-ai-examples
• Smithery: https://smithery.ai/server/fabiosuizu/pronunciation-assessment
• MCPize: https://mcpize.com/mcp/speech-ai

Files Added

• plugins/wasm-go/mcp-servers/mcp-speech-ai/mcp-server.yaml - Server configuration with 4 tools
• plugins/wasm-go/mcp-servers/mcp-speech-ai/README.md - English documentation
• plugins/wasm-go/mcp-servers/mcp-speech-ai/README_ZH.md - Chinese documentation

Reference: Issue #2113 (How to publish your MCP Server)

[CLAassistant]

All committers have signed the CLA.

[fasuizu-br]

recheck

[fasuizu-br]

Hi team! Just a friendly check-in on this PR. The CLA has been signed and all checks are passing. This adds a Speech AI MCP server plugin (pronunciation assessment, TTS, STT) using Higress's declarative YAML format with request/response templates. Happy to address any feedback or make adjustments. Thank you for your time!

[fasuizu-br]

recheck