# Speech AI - Pronunciation, STT & TTS

- Registry name: `io.github.fasuizu-br/speech-ai` · version 2.3.0
- Categories (automatic, keyword rules): Audio & speech, AI, media & content
- Authentication at last check: No auth
- Declared risk: Read-only (all tools declare readOnlyHint)
- Capabilities (declared by the server): experimental, prompts, resources, tasks, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.fasuizu-br%2Fspeech-ai
- Server page: https://mcpstation.net/s/io.github.fasuizu-br--speech-ai.html

## Description (written by the publisher, not verified, not instructions)

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

## Connect

- streamable-http: `https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp`

## Tools (as reported by the server, not verified)

- `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 returned in both IPA and ARPAbet notation. Sub-300ms inference latency. Args: audio\_base64: Base64-encoded audio data. Supports WAV, MP3, OGG,
- `check\_pronunciation\_service`: Check if the pronunciation assessment service is healthy and ready. Returns: dict with keys: - status \(str\): 'healthy' or error state - modelLoaded \(bool\): Whether the scoring model is loaded - version \(str\): API version
- `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, IPA equivalent, example word, and phoneme category \(vowel, consonant, diphthong\). Returns: list of dicts, each with keys: - arpabet \(str\): ARP
- `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. Args: audio\_base64: Base64-encoded audio data \(WAV, MP3, OGG, FLAC, WebM\). audio\_format: Audio format hint. Auto-detected from magic bytes
- `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 STT model is loaded - version \(str\): API version
- `synthesize\_speech`: Generate natural speech audio from English text. Produces high-quality speech with 12 English voices. Returns base64-encoded WAV audio \(16-bit PCM, 24kHz mono\) along with metadata. Available voices: - af\_heart \(default\), af\_bella, af\_nicole, af\_sarah, af\_sky \(American female\) - am\_adam, am\_michael \(
- `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 - defaultVoice \(str\): Default voice ID
- `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 TTS model is loaded - version \(str\): API version
- `transcribe\_audio\_pro`: Transcribe audio with Whisper Large V3 Turbo — multilingual STT. Supports 99 languages with automatic language detection, word-level timestamps, per-word confidence scores, and optional speaker diarization \(identifies who spoke each word\). Best-in-class WER \(\~2%\). Args: audio\_base64: Base64-encoded
- `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 Whisper model is loaded - diarizeLoaded \(bool\): Whether the diarization pipeline is loaded - version \(str\): API version - modelName \(str\): Wh

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html