Speech AI - Pronunciation, STT & TTS

Official10 toolsLive

by fasuizu-br · JavaScript

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

io.github.fasuizu-br/speech-ai MCP Server

This MCP server provides pronunciation scoring, speech-to-text, and text-to-speech for language learning. It targets multiple speech workflows and includes a readme excerpt referencing a current TTS health endpoint and a current Brainiall TTS MCP repository. The repo excerpt indicates legacy URLs were retired.

🛠️ Key Features

Pronunciation scoring
Speech-to-text
Text-to-speech
Speaker diarization

🚀 Use Cases

Language learning with speech input and audio output
Pronunciation evaluation
Converting spoken language to text (speech-to-text)
Generating spoken responses (text-to-speech)

⚡ Developer Benefits

10 tools exposed by the server
Topic coverage includes API examples and webVTT
Includes a documented TTS health check link

⚠️ Limitations

The readme excerpt states the repository is legacy
Former gateway/old MCP URLs (e.g., apim-ai-apis.azure-api.net and older Speech AI MCP URLs) are retired and should not be used

Topics

ai-agentsapi-exampleslanguage-learningmcppronunciationspeech-aispeech-to-texttext-to-speechpt-brspeaker-diarizationsynthetic-testingwebvtt

Captured live from the server via tools/list.

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 — 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.)

Parameters3

audio_base64	string	required	Base64-encoded audio data. Supports WAV, MP3, OGG, and WebM formats.
text	string	required	The reference English text that the speaker was expected to read aloud.
audio_format	string	optional	Audio format hint — one of 'wav', 'mp3', 'ogg', 'webm'.

Raw schema

{
  "type": "object",
  "properties": {
    "audio_base64": {
      "description": "Base64-encoded audio data. Supports WAV, MP3, OGG, and WebM formats.",
      "maxLength": 20000000,
      "type": "string"
    },
    "text": {
      "description": "The reference English text that the speaker was expected to read aloud.",
      "maxLength": 10000,
      "type": "string"
    },
    "audio_format": {
      "default": "wav",
      "description": "Audio format hint — one of 'wav', 'mp3', 'ogg', 'webm'.",
      "type": "string"
    }
  },
  "required": [
    "audio_base64",
    "text"
  ]
}

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

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

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

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

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.)

Parameters3

audio_base64	string	required	Base64-encoded audio data. Supports WAV, MP3, OGG, FLAC, and WebM formats.
audio_format	any	optional	Audio format hint — 'wav', 'mp3', 'ogg', 'flac', 'webm'. Auto-detected if omitted.
include_timestamps	boolean	optional	If true, include word-level start/end times and confidence.

Raw schema

{
  "type": "object",
  "properties": {
    "audio_base64": {
      "description": "Base64-encoded audio data. Supports WAV, MP3, OGG, FLAC, and WebM formats.",
      "maxLength": 20000000,
      "type": "string"
    },
    "audio_format": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Audio format hint — 'wav', 'mp3', 'ogg', 'flac', 'webm'. Auto-detected if omitted."
    },
    "include_timestamps": {
      "default": true,
      "description": "If true, include word-level start/end times and confidence.",
      "type": "boolean"
    }
  },
  "required": [
    "audio_base64"
  ]
}

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

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

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

Parameters3

text	string	required	English text to convert to speech. Max 5000 characters.
voice	any	optional	Voice ID (e.g. 'af_heart', 'am_adam'). Uses default if omitted.
speed	number	optional	Speech speed multiplier (0.5 = half speed, 2.0 = double).

Raw schema

{
  "type": "object",
  "properties": {
    "text": {
      "description": "English text to convert to speech. Max 5000 characters.",
      "maxLength": 5000,
      "type": "string"
    },
    "voice": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Voice ID (e.g. 'af_heart', 'am_adam'). Uses default if omitted."
    },
    "speed": {
      "default": 1,
      "description": "Speech speed multiplier (0.5 = half speed, 2.0 = double).",
      "type": "number"
    }
  },
  "required": [
    "text"
  ]
}

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

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

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

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

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 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.)

Parameters3

audio_base64	string	required	Base64-encoded audio data. Supports WAV, MP3, OGG, FLAC, and WebM formats.
language	any	optional	Language code (e.g. 'en', 'es', 'zh'). Auto-detected when omitted.
diarize	boolean	optional	Enable speaker diarization to identify who spoke each word.

Raw schema

{
  "type": "object",
  "properties": {
    "audio_base64": {
      "description": "Base64-encoded audio data. Supports WAV, MP3, OGG, FLAC, and WebM formats.",
      "maxLength": 20000000,
      "type": "string"
    },
    "language": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Language code (e.g. 'en', 'es', 'zh'). Auto-detected when omitted."
    },
    "diarize": {
      "default": false,
      "description": "Enable speaker diarization to identify who spoke each word.",
      "type": "boolean"
    }
  },
  "required": [
    "audio_base64"
  ]
}

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')

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

README.md3 KBView on GitHub

Brainiall Speech AI examples — migration notice

This repository is legacy. The former apim-ai-apis.azure-api.net gateway and the old Speech AI MCP URLs documented in earlier revisions have been retired. Do not use those URLs. The other files in this repository are retained only as historical source and may no longer run.

Current supported surfaces

Need	Current surface
Text-to-speech MCP server	`https://api.brainiall.com/mcp/tts/mcp`
Text-to-speech REST endpoint	`POST https://api.brainiall.com/v1/tts/synthesize`
TTS health check	`https://api.brainiall.com/mcp/tts/health`
TTS setup, OpenAPI and maintained examples	`fasuizu-br/brainiall-tts-mcp`
Brazilian Portuguese transcription	Transcreve BR
Speech-to-text API overview	Brainiall Speech-to-Text
Account and API key	Brainiall app
Offline contract compatibility checks	`compatibility-pack/`

Authentication for the current API uses an Authorization: Bearer YOUR_BRAINIALL_API_KEY header. Never commit a real key.

For TTS examples for Claude, Cursor, VS Code, n8n, Postman and raw REST clients, use the maintained TTS repository linked above. It is the canonical source for current voices, prices and request schemas.

The small compatibility pack is different from the historical examples. It is an offline-only contract test for buffered TTS, generic diarized-STT review artifacts, a synthetic diarization canary and local-by-default usage planning. It performs no API call during tests, contains no key, copies no third-party source, and does not claim streaming, cancellation, OpenAI drop-in compatibility, completed third-party integration or billing. Read its kill gates before reusing it.

Why this notice exists

External directories and search engines may still link to this repository. This notice prevents an old listing from sending developers to endpoints that no longer work and points them to the maintained production surfaces.

License

MIT — Brainiall

C112 — hosted STT contract fixture

The Whisper-WebUI OpenAI-compatible fixture is a provider-neutral, synthetic request/response example for maintainers evaluating an external speech-to-text path. It does not claim that Whisper-WebUI has adopted the contract, and it never includes a key or private audio.

Install

Tools (10)

assess_pronunciationcheck_pronunciation_serviceget_phoneme_inventorytranscribe_audiocheck_stt_servicesynthesize_speechlist_tts_voicescheck_tts_service

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

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

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "speech-ai": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

io.github.fasuizu-br/speech-ai MCP Server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

assess_pronunciation

check_pronunciation_service

get_phoneme_inventory

transcribe_audio

check_stt_service

synthesize_speech

list_tts_voices

check_tts_service

transcribe_audio_pro

check_whisper_service

Brainiall Speech AI examples — migration notice

Current supported surfaces

Why this notice exists

License

C112 — hosted STT contract fixture

Install

Remote endpoint

Related servers