Speech AI - Pronunciation, STT & TTS is an MCP server with 10 tools an agent can call, among them assess_pronunciation, check_pronunciation_service, check_stt_service. It answers at https://pronunciation-mcp.thankfulfield-a7857897.eastus.azurecontainerapps.io/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 10 times since 5 September 2026; the last check, on 18 October 2026, succeeded.
Pronunciation scoring, speech-to-text, and text-to-speech for language learning
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
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: audi Inputs: audio_base64, text, audio_format |
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 |
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 |
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 |
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 |
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). |
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 |
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 Inputs: text, voice, speed |
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). audi Inputs: audio_base64, audio_format, include_timestamps |
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). Inputs: audio_base64, language, diarize |
Every block below points at https://pronunciation-mcp.thankfulfield-a7857897.eastus.azurecontainerapps.io/mcp. Pick your client and copy.
claude mcp add --transport http speech-ai-pronunciation-stt-tts https://pronunciation-mcp.thankfulfield-a7857897.eastus.azurecontainerapps.io/mcp
{
"mcpServers": {
"speech-ai-pronunciation-stt-tts": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://pronunciation-mcp.thankfulfield-a7857897.eastus.azurecontainerapps.io/mcp"]
}
}
}{
"mcpServers": {
"speech-ai-pronunciation-stt-tts": {
"url": "https://pronunciation-mcp.thankfulfield-a7857897.eastus.azurecontainerapps.io/mcp"
}
}
}{
"servers": {
"speech-ai-pronunciation-stt-tts": {
"type": "http",
"url": "https://pronunciation-mcp.thankfulfield-a7857897.eastus.azurecontainerapps.io/mcp"
}
}
}{
"context_servers": {
"speech-ai-pronunciation-stt-tts": {
"url": "https://pronunciation-mcp.thankfulfield-a7857897.eastus.azurecontainerapps.io/mcp"
}
}
}{
"mcpServers": {
"speech-ai-pronunciation-stt-tts": {
"serverUrl": "https://pronunciation-mcp.thankfulfield-a7857897.eastus.azurecontainerapps.io/mcp"
}
}
}{
"mcpServers": {
"speech-ai-pronunciation-stt-tts": {
"url": "https://pronunciation-mcp.thankfulfield-a7857897.eastus.azurecontainerapps.io/mcp"
}
}
}name: Speech AI - Pronunciation, STT & TTS
version: 0.0.1
schema: v1
mcpServers:
- name: Speech AI - Pronunciation, STT & TTS
type: streamable-http
url: https://pronunciation-mcp.thankfulfield-a7857897.eastus.azurecontainerapps.io/mcp{
"mcpServers": {
"speech-ai-pronunciation-stt-tts": {
"httpUrl": "https://pronunciation-mcp.thankfulfield-a7857897.eastus.azurecontainerapps.io/mcp"
}
}
}{
"mcpServers": {
"speech-ai-pronunciation-stt-tts": {
"type": "http",
"url": "https://pronunciation-mcp.thankfulfield-a7857897.eastus.azurecontainerapps.io/mcp"
}
}
}{
"mcpServers": {
"speech-ai-pronunciation-stt-tts": {
"url": "https://pronunciation-mcp.thankfulfield-a7857897.eastus.azurecontainerapps.io/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fpronunciation-mcp.thankfulfield-a7857897.eastus.azurecontainerapps.io%2Fmcp&type=streamable_http&id=speech-ai-pronunciation-stt-tts&name=Speech%20AI%20-%20Pronunciation%2C%20STT%20%26%20TTS
It answered our last check on 18 October 2026 in 319 ms. Over 10 checks since 5 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
10, as returned by the server's own tools/list on 31 August 2026: assess_pronunciation, check_pronunciation_service, check_stt_service, check_tts_service, check_whisper_service, get_phoneme_inventory, list_tts_voices, synthesize_speech, and 2 more.
It answered our last check on 18 October 2026 in 319 ms. Over 10 checks since 5 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://pronunciation-mcp.thankfulfield-a7857897.eastus.azurecontainerapps.io/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.fasuizu-br. Endpoint host: pronunciation-mcp.thankfulfield-a7857897.eastus.azurecontainerapps.io. ARD identifier: urn:air:io.github.fasuizu-br:mcp:speech-ai.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.