# Fasuizu Br Speech Ai MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.fasuizu-br%2Fspeech-ai
Registry id: `mcp-registry/io.github.fasuizu-br/speech-ai`
Status: live (checked 2026-10-27T02:16:36.052Z)

## Measurements (30 days)

- Uptime: 87.78%
- Checks: 5557
- Outages (90 days): 3147

## Install

```json
{
  "mcpServers": {
    "fasuizu-br-speech-ai-mcp-server": {
      "type": "http",
      "url": "https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http fasuizu-br-speech-ai-mcp-server https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp
```

## Tools (10)

- `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 re
- `check_pronunciation_service`: Check if the pronunciation assessment service is healthy and ready. Returns: dict with keys: - status (str): 'healthy' or error state - modelLoaded (bool): Whet
- `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 (bool): Whether the ST
- `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 (bool): Whether the TT
- `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 (bool): Whether the W
- `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, IP
- `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, accent, grade - 
- `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) 
- `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.
- `transcribe_audio_pro`: Transcribe audio with Whisper Large V3 Turbo — multilingual STT. Supports 99 languages with automatic language detection, word-level timestamps, per-word confid

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.