List your agent

Speech AI - Pronunciation, STT & TTS

MCP server● Hosted · onlinev2.3.0

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

Reviews

No review yet. Used Speech AI - Pronunciation, STT & TTS? Be the first to help others choose.

What it does

Speech AI - Pronunciation, STT & TTS is an MCP server, a connector that lets an AI assistant use it as a tool. It is hosted: an assistant connects to it over the internet, nothing to install.

No capability identified yet from its description.

Facts come from the Official MCP Registry, as declared by the publisher. Capabilities are matched automatically (low confidence). None of this is a test of the tool.

At a glance

Hosted (remote)YES
Local installNO
Version2.3.0
PriceNot in the registry
First seen26 Sept 2026
Last checked1d ago

How to connect

As declared in the Official MCP Registry · hosted endpoint tested by Electra Index 22h ago (live check)

Hosted endpoint

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

In Claude Code: claude mcp add --transport http image-tools-background-removal-upscaling-face-restoration https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp

MCP settings (Claude Desktop, Cursor and other MCP clients)

{
  "mcpServers": {
    "image-tools-background-removal-upscaling-face-restoration": {
      "url": "https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp"
    }
  }
}

Live check

Electra Index connected to the hosted endpoint 22h ago

ONLINE Speech AI - Pronunciation, STT & TTS answered an MCP connection on 16 Nov 2026 and introduced itself as speech-ai 2.14.5 (MCP protocol 2025-06-18).

10 tools offered to AI assistants

  • 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
  • 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
  • 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).
  • 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
  • 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
  • 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
  • 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
  • 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
  • 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).
  • 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

What "online" means: the server answered an MCP connection at the time of the check. It is not a guarantee of security, quality or continuous uptime. How we test: we open an MCP session and ask for the tool list, as an AI assistant would. We never run a tool and never send a key. Checked every few days. Method

Is this your server? Monitoring Pro: a check every 30 minutes and an email within the hour when it stops answering. Launch offer: $39.99 once, for life.

Facts & evidence

Each fact shows where it was seen and when.
FactValueEvidenceSourceLast confirmed
Hosted endpointhttps://apim-ai-apis.azure-api.net/mcp/pronunciation/mcpDECLAREDSRC-001 Official MCP Registry1d ago
Version2.3.0DECLAREDSRC-001 Official MCP Registry1d ago
Local install (package)noDECLAREDSRC-001 Official MCP Registry1d ago
Remote access (hosted)yesDECLAREDSRC-001 Official MCP Registry1d ago
Websitehttps://brainiall.comDECLAREDSRC-001 Official MCP Registry1d ago
Repositoryhttps://github.com/fasuizu-br/speech-ai-examplesDECLAREDSRC-001 Official MCP Registry1d ago
Registry statusactiveDECLAREDSRC-001 Official MCP Registry1d ago
MCP serveryesDECLAREDSRC-001 Official MCP Registry1d ago

Change history

  • VERSION26 Oct 2026
    1.1.0 → 2.3.0
  • VERSION26 Oct 2026
    2.3.0 → 1.1.0
  • VERSION19 Oct 2026
    1.1.0 → 2.3.0
  • VERSION19 Oct 2026
    2.3.0 → 1.1.0
  • VERSION12 Oct 2026
    1.1.0 → 2.3.0
  • VERSION12 Oct 2026
    2.3.0 → 1.1.0
  • VERSION05 Oct 2026
    1.1.0 → 2.3.0
  • VERSION05 Oct 2026
    2.3.0 → 1.1.0
  • VERSION28 Sept 2026
    1.1.0 → 2.3.0
  • VERSION28 Sept 2026
    2.3.0 → 1.1.0
  • VERSION26 Sept 2026
    1.1.0 → 2.3.0

Is this page accurate?

Flag it and our robot re-checks the official source. Reports never change a score.

Do you run Speech AI - Pronunciation, STT & TTS? Know when it stops answering

For publishers · optional

Its hosted endpoint can be monitored. Monitoring Pro connects every 30 minutes like an AI assistant, emails you within the hour when it stops answering, keeps a 90-day availability history and adds your answer rate to your badge.

Monitor Speech AI - Pronunciation, STT & TTSLaunch offer $39.99 once, for life instead of $9.99/month · All plans

Monitoring never changes a score or a rank.

Are you the publisher of Speech AI - Pronunciation, STT & TTS?

Free · show your listing

An independent listing builds trust with your buyers. Announce it, and add the badge to your website or README.

Announce it on LinkedIn
Listed on Electra IndexListed on Electra Index
<a href="https://electraindex.com/mcp/image-tools-background-removal-upscaling-face-restoration?utm_source=badge&utm_medium=share&utm_campaign=listing"><img src="https://electraindex.com/api/badge/image-tools-background-removal-upscaling-face-restoration/card" width="260" height="72" alt="Listed on Electra Index"></a>

Questions about Speech AI - Pronunciation, STT & TTS

How do I connect Speech AI - Pronunciation, STT & TTS?

Use the hosted endpoint https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp in your assistant's MCP settings. The exact settings are in "How to connect" above, as declared in the Official MCP Registry.

What tools does Speech AI - Pronunciation, STT & TTS offer?

When Electra Index connected on 16 Nov 2026, it listed 10 tools: assess_pronunciation, check_pronunciation_service, get_phoneme_inventory, transcribe_audio, check_stt_service, synthesize_speech, list_tts_voices, check_tts_service and more. The full list is in "Live check" above.

Is Speech AI - Pronunciation, STT & TTS online?

Yes. Its hosted endpoint answered an MCP connection from Electra Index 22h ago.