MCP server

Speech AI - Pronunciation, STT & TTS

io.github.fasuizu-br/speech-ai

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

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

Website Source

At a glance

Type

MCP server

Publisher

Not verified

Status

Working at last check

Tools

10

Token cost

About 2,530 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

26 Oct 2026, 08:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http speech-ai https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.speech-ai]
url = "https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp"

Gemini CLI

{"mcpServers":{"speech-ai":{"httpUrl":"https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp"}}}

Cursor

{"mcpServers":{"speech-ai":{"url":"https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp"}}}

VS Code

{"servers":{"speech-ai":{"type":"http","url":"https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp"}}}

Antigravity

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

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"speech-ai","server_url":"https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"speech-ai","server_url":"https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp"}

Tools

• assess_pronunciation ~496 tokens
  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
• check_pronunciation_service ~103 tokens
  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
• check_stt_service ~96 tokens
  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
• check_tts_service ~96 tokens
  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
• check_whisper_service ~141 tokens
  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 (st
• get_phoneme_inventory ~173 tokens
  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: - arpa
• list_tts_voices ~90 tokens
  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
• synthesize_speech ~406 tokens
  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
• transcribe_audio ~444 tokens
  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 ma
• transcribe_audio_pro ~485 tokens
  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-en

Browse

• GitHub tools
• GitHub and code hosting
• Text to speech
• Speech to text

Related MCP servers

• Brainiall Pronunciation
  Pronunciation assessment, phoneme scoring, speaker voice ID, audio transcription, speech synthesis.
• ElevenLabs
  ElevenLabs in natural language: generate speech in any language, create and manage voices, compose m
• Tutorializer Video Tutorials
  Write and update video tutorials, voiceovers and pronunciation rules across your projects.
• Crypto, web, finance and app data tools
  179 tools: crypto, EVM, SEC, FDA, NHTSA VIN, NWS weather, Eurostat, FRED, cloud & LLM prices, DNS.
• Clueso
  Make videos and docs with your AI agent — describe what you need, every output stays editable.
• Tanod ML
  Local ML: speech to text (SRT/VTT), text embeddings, reranking, similarity, entities, zero-shot.
• Speakeroo speaking coach
  AI speaking coach: feedback on speeches from text or audio, plus topics, pronunciation and rubrics.
• Wikexa Knowledge
  Wikipedia, Wikidata and Wiktionary as clean JSON, not HTML. 1.9M searchable. Free, no auth.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/io.github.fasuizu-br/speech-ai.svg)](https://aptlynx.net/servers/io.github.fasuizu-br/speech-ai)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents