MCP serverio.github.fasuizu-br/speech-ai

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

UNRATEDActivestreamable-httpapim-ai-apis.azure-api.net

Overview

Score?

UNRATED 0.615

of what a free look can see, on 29 looks

Looks

last 2 hr ago

Tools

More info

URL

apim-ai-apis.azure-api.net/mcp/pronunciation/mcp

streamable-http

Says it is

speech-ai 2.14.5

protocol 2025-06-18

In the record since

32 days ago

Among servers18,413 with a card

0median 0.606 · this server 0.615 · highest on record 0.8561

Toolsfrom sha256:bc41b31275…86aadd

The tools this server lists, read out of the definition it returned
Tool	Schema
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	input · no output
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): Whe	input · no output
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 S	input · no output
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 T	input · no output
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	input · no output
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, examp	input · no output
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 -	input · no output
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	input · no output
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_b	input · no output
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 op	input · no output

Verify it yourselfnpx teppi-check https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcpcurl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M1FZ2F9TE7BM8CKJ0591NWYN