MCP Server
Speech AI - Pronunciation, STT & TTS
io.github.fasuizu-br/speech-ai
What this MCP does
Supports English pronunciation assessment, multilingual speech transcription, text-to-speech synthesis, and phoneme reference data for language learning.
Capabilities
Tools
10
tools
assess_pronunciation
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, and WebM formats.
text: The reference English text that the speaker was expected to read aloud.
audio_format: Audio format hint â one of 'wav', 'mp3', 'ogg', 'webm'. Defaults to 'wav'.
Returns:
dict with keys:
- overallScore (int 0-100): Overall pronunciation quality
- sentenceScore (int 0-100): Sentence-level fluency and accuracy
- words (list): Per-word scores, each containing:
- word (str): The word
- score (int 0-100): Word pronunciation score
- phonemes (list): Per-phoneme scores with IPA/ARPAbet notation
- decodedTranscript (str): What the model heard (ASR transcript)
- transcript (str): Reference text
- confidence (float 0-1): Scoring confidence
- warnings (list[str]): Quality warnings if any
- audioQuality (dict): Audio metrics (SNR, peak/RMS dB, etc.)
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['audio_base64', 'text'], 'properties': {'text': {'type': 'string', 'maxLength': 10000, 'description': 'The reference English text that the speaker was expected to read aloud.'}, 'audio_base64': {'type': 'string', 'maxLength': 20000000, 'description': 'Base64-encoded audio data. Supports WAV, MP3, OGG, and WebM formats.'}, 'audio_format': {'type': 'string', 'default': 'wav', 'description': "Audio format hint â\x80\x94 one of 'wav', 'mp3', 'ogg', 'webm'."}}}
check_pronunciation_service
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
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'properties': {}}
check_stt_service
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
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'properties': {}}
check_tts_service
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
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'properties': {}}
check_whisper_service
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): Whisper model name (e.g. 'large-v3-turbo')
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'properties': {}}
get_phoneme_inventory
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): ARPAbet symbol (e.g. 'AA', 'TH')
- ipa (str): IPA notation
- example (str): Example word containing the phoneme
- category (str): vowel, consonant, or diphthong
Read only
Idempotent
Input schema
{'type': 'object', 'properties': {}}
list_tts_voices
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
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'properties': {}}
synthesize_speech
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 (American male)
- bf_emma, bf_isabella (British female)
- bm_george, bm_lewis, bm_daniel (British male)
Args:
text: English text to synthesize (1-5000 characters).
voice: Voice ID. See list above. Defaults to 'af_heart'.
speed: Speed multiplier from 0.5 to 2.0 (default: 1.0).
Returns:
dict with keys:
- audio_base64 (str): Base64-encoded WAV audio (16-bit PCM, 24kHz)
- duration_ms (str): Audio duration in milliseconds
- voice (str): Voice ID used
- text_length (str): Input text character count
- processing_ms (str): Synthesis time in milliseconds
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['text'], 'properties': {'text': {'type': 'string', 'maxLength': 5000, 'description': 'English text to convert to speech. Max 5000 characters.'}, 'speed': {'type': 'number', 'default': 1.0, 'description': 'Speech speed multiplier (0.5 = half speed, 2.0 = double).'}, 'voice': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': "Voice ID (e.g. 'af_heart', 'am_adam'). Uses default if omitted."}}}
transcribe_audio
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 if omitted.
include_timestamps: Whether to include word-level timing (default: true).
Returns:
dict with keys:
- text (str): Full decoded transcript
- words (list): Per-word results with timestamps, each containing:
- word (str): The transcribed word
- start (float): Start time in seconds
- end (float): End time in seconds
- confidence (float 0-1): Word-level confidence
- audioDurationMs (int): Audio duration in milliseconds
- metadata (dict): Processing time, audio length, model version
- audioQuality (dict): Audio metrics (SNR, peak/RMS dB, etc.)
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['audio_base64'], 'properties': {'audio_base64': {'type': 'string', 'maxLength': 20000000, 'description': 'Base64-encoded audio data. Supports WAV, MP3, OGG, FLAC, and WebM formats.'}, 'audio_format': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': "Audio format hint â\x80\x94 'wav', 'mp3', 'ogg', 'flac', 'webm'. Auto-detected if omitted."}, 'include_timestamps': {'type': 'boolean', 'default': True, 'description': 'If true, include word-level start/end times and confidence.'}}}
transcribe_audio_pro
Transcribe Audio Pro (Whisper)
Transcribe audio with Whisper Large V3 Turbo â 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 audio (WAV, MP3, OGG, FLAC, WebM).
language: Language code. Auto-detected if omitted. Supports 99 languages.
diarize: Enable speaker diarization (default: false). When true, each word
includes a speaker label (e.g. SPEAKER_00, SPEAKER_01).
Returns:
dict with keys:
- text (str): Full decoded transcript
- words (list): Per-word results with timestamps, each containing:
- word (str), start (float), end (float), confidence (float 0-1)
- speaker (str|null): Speaker label when diarize=true
- speakers (dict|null): Speaker info with count and labels
- audioDurationMs (int): Audio duration in milliseconds
- metadata (dict): Processing time, language, languageProbability
- audioQuality (dict): Audio metrics (SNR, peak/RMS dB, etc.)
Read only
Open world
Idempotent
Input schema
{'type': 'object', 'required': ['audio_base64'], 'properties': {'diarize': {'type': 'boolean', 'default': False, 'description': 'Enable speaker diarization to identify who spoke each word.'}, 'language': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': "Language code (e.g. 'en', 'es', 'zh'). Auto-detected when omitted."}, 'audio_base64': {'type': 'string', 'maxLength': 20000000, 'description': 'Base64-encoded audio data. Supports WAV, MP3, OGG, FLAC, and WebM formats.'}}}
History
Recent tool changes
Added
check_whisper_service
Sept. 21, 2026, 2:41 a.m.
Added
transcribe_audio_pro
Sept. 21, 2026, 2:41 a.m.
Added
check_tts_service
Sept. 21, 2026, 2:41 a.m.
Added
list_tts_voices
Sept. 21, 2026, 2:41 a.m.
Added
synthesize_speech
Sept. 21, 2026, 2:41 a.m.
Added
check_stt_service
Sept. 21, 2026, 2:41 a.m.
Added
transcribe_audio
Sept. 21, 2026, 2:41 a.m.
Added
get_phoneme_inventory
Sept. 21, 2026, 2:41 a.m.
Added
check_pronunciation_service
Sept. 21, 2026, 2:41 a.m.
Added
assess_pronunciation
Sept. 21, 2026, 2:41 a.m.
Discover
Similar MCP servers
Riddle
com.riddle/creator
Builds, edits, publishes, embeds, and analyzes quizzes, polls, forms, personality tests, and related question banks.
api
video.quiz/api
Creates, manages, AI-generates, and renders quiz and flashcard videos, including templates and downloadable video outputs.
PodLearn
io.github.blutrich/podlearn
Searches podcasts and YouTube, transcribes episodes, searches transcripts, generates structured lessons, and creates LinkedIn pos…
Tutorializer Video Tutorials
com.tutorializer/tutorializer
Manages localized tutorials, voiceover segments, pronunciation rules, and registered rendered tutorial videos.
Escola de Rádio TV & Web (ER+)
br.com.escoladeradio.www/public
Provides read-only access to a Brazilian radio school's courses, classes, teachers, podcasts, blog, services, and availability.
Brainiall Pronunciation
com.brainiall/pronunciation
Assesses English pronunciation, transcribes audio, identifies speakers by voiceprint and synthesizes English speech in multiple v…
QuizBase
com.runriva.quizbase/mcp
Searches, filters, samples, and manages a large multilingual catalog of trivia questions with categories, topics, provenance, and…
Soluble(s) — Podcast de journalisme de solutions
io.github.petitsolu/solubles
Searches French solutions-journalism podcast episodes and transcripts, including child-friendly versions and practical actions.