# Brainiall Pronunciation MCP server

Source: https://glimind.com/server/mcp-registry%2Fcom.brainiall%2Fpronunciation
Registry id: `mcp-registry/com.brainiall/pronunciation`
Status: live (checked 2026-11-22T19:04:39.727Z)

## Verdict

Brainiall Pronunciation MCP server answered 100% of Glimind's liveness checks over 30 days, better than 43% of MCP servers, with 617 ms median handshake and 5 outages in 90 days. Its agent-readiness grade is A (96/100) across 14 tools, costing an agent about 2,490 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 100% | 43% of MCP servers |
| Median handshake latency | 617 ms | 16% of MCP servers |
| p95 handshake latency | 747 ms | — |
| Checks in 30 days | 6,878 | — |
| Outages, 90 days | 5 | — |
| Median recovery | 8 min | — |
| Agent-readiness score | 96/100 (A) | 74% of MCP servers |
| Tools | 14 | — |
| Tool-list size for an agent | ~2,490 tokens | 42% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "brainiall-pronunciation-mcp-server": {
      "type": "http",
      "url": "https://api.brainiall.com/mcp/pronunciation/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http brainiall-pronunciation-mcp-server https://api.brainiall.com/mcp/pronunciation/mcp
```

## Tools (14)

- `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 Brainiall Pronunciation service is healthy and ready. Returns: dict with keys: - status (str): 'healthy' or error state - modelLoaded (bool): Wheth
- `check_stt_service`: Check if the Brainiall Speech service is healthy and ready. Returns: dict with keys: - status (str): 'healthy' or error state - modelLoaded (bool): Whether the 
- `check_tts_service`: Check if the Brainiall Voice service is healthy and ready. Returns: dict with keys: - status (str): 'healthy' or error state - modelLoaded (bool): Whether the s
- `check_whisper_service`: Check if the Brainiall Speech Pro service is healthy and ready. Returns: dict with keys: - status (str): 'healthy' or error state - modelLoaded (bool): Whether 
- `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 Brainiall Voice synthesis voices with metadata. Returns: dict with keys: - voices (list): Available voices, each with id, name, gender, accen
- `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 Brainiall Speech Pro — multilingual transcription. Supports 99 languages with automatic language detection, word-level timestamps, per-wor
- `voice_id_enroll`: Enroll a voiceprint for a speaker from ~2s of clear speech. Repeat with more clips to strengthen it. Only an irreversible embedding is stored — never the raw au
- `voice_id_identify`: 1:N identification — rank everyone enrolled in the group against this clip. Returns: dict with keys: candidates (list of {speaker_id, similarity}, best first).
- `voice_id_list_speakers`: List the speakers enrolled in a group. Returns: dict with keys: speakers (list of {speaker_id, n_samples, ...}).
- `voice_id_verify`: 1:1 verification — is this clip the enrolled speaker? Returns: dict with keys: similarity (float), match (bool), threshold (float).

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