io.github.fasuizu-br/speech-ai

up checked 2026-11-11T10:39:25.993Z

Unclaimed · Unverified

Agent searches it appeared in, last 30 days: 1. Run this server? Claim the listing: verified label, uptime alerts and analytics.

Publisher-provided title

Speech AI - Pronunciation, STT & TTS

Publisher-provided description

Pronunciation scoring, speech-to-text, and text-to-speech for language learning

Summary by lookupd

Score English pronunciation from audio, transcribe speech to text with timestamps, and synthesize English speech across 12 voices.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http speech-ai https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp

Codex, remote (streamable-http)

codex mcp add speech-ai --url https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "speech-ai": {
      "url": "https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp"
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Tools (10 tools)

Publisher-provided text

• assess_pronunciation Assess English pronunciation quality from audio. Scores pronunciation at four levels: overall, sentence, word, and phoneme. Each score is 0-100. Phonemes are r
• check_pronunciation_service Check if the pronunciation assessment service is healthy and ready. Returns: dict with keys: - status (str): 'healthy' or error state - mod
• get_phoneme_inventory Get the full phoneme inventory supported by the pronunciation scorer. Returns a list of all English phonemes the engine can assess, including ARPAbet symbol, I
• transcribe_audio Transcribe audio to text with word-level timestamps. Converts spoken English audio into text with optional word-level timestamps and per-word confidence scores
• check_stt_service Check if the speech-to-text service is healthy and ready. Returns: dict with keys: - status (str): 'healthy' or error state - modelLoaded (
• synthesize_speech Generate natural speech audio from English text. Produces high-quality speech with 12 English voices. Returns base64-encoded WAV audio (16-bit PCM, 24kHz mono)
• list_tts_voices List all available text-to-speech voices with metadata. Returns: dict with keys: - voices (list): Available voices, each with id, name, gender, acc
• check_tts_service Check if the text-to-speech service is healthy and ready. Returns: dict with keys: - status (str): 'healthy' or error state - modelLoaded (
• transcribe_audio_pro Transcribe audio with Whisper Large V3 Turbo — multilingual STT. Supports 99 languages with automatic language detection, word-level timestamps, per-word confi
• check_whisper_service Check if the Whisper STT Pro service is healthy and ready. Returns: dict with keys: - status (str): 'healthy' or error state - modelLoaded

Details

• Version: 2.3.0
• Transports: streamable-http
• Uptime (7 days): 100%
• Median latency: 293 ms
• First indexed: 2026-11-01T09:29:30.345Z
• Last seen in registry: 2026-11-01T09:29:30.397Z
• Repository: https://github.com/fasuizu-br/speech-ai-examples
• Website: https://brainiall.com

Badge for your README

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/io.github.fasuizu-br/speech-ai.svg)](https://lookupd.com/servers/io.github.fasuizu-br/speech-ai)

• 62033 servers
• Last crawl: 2026-11-11T15:38:39.561Z
• API base: https://api.lookupd.com
• MCP URL: https://api.lookupd.com/mcp