Skip to content
External endpointresponds

Speech AI - Pronunciation, STT & TTS

Pronunciation scoring, speech-to-text, and text-to-speech for AI agents.

Endpoint URL
https://pronunciation-mcp.thankfulfield-a7857897.eastus.azurecontainerapps.io/mcp
Current status
responds
Last checked
Aug 17, 2026, 05:06 AM UTC
Check
MCP initialize · 8s limit
Latency
898 ms
Response record
4 of 4 rounds
Transport
streamable-http
Source
mcp_registry
Registry name
io.github.fasuizu-br/speech-ai

Current observation

This endpoint answered at its latest recorded check.

What this server reports about itself

Self-reported at initialize. Not verified by Licium.

Server name
speech-ai
Version
2.14.5
Capability keys
experimental, prompts, resources, tools, tasks
Tool names
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
Instructions excerpt

Speech AI API suite with 4 capabilities: 1. **Pronunciation Assessment** — assess_pronunciation scores English pronunciation from audio at overall, sentence, word, and phoneme levels (0-100). 2. **Speech-to-Text** — transcribe_audio converts audio to text with word-level timestamps and confidence scores. 3. **Text-to-Speech** — synthesize_speech generates natural speech audio from text with 12 English voices, speed control, and WAV output. 4. **Whisper STT Pro** — transcribe_audio_pro uses Whisper Large V3 Turbo for 99-language transcription with optional speaker diarization. All tools accept base64-encoded audio. Read the resources for guides and requirements.

Reported Aug 17, 2026, 05:06 AM UTC.

Check history

Oldest to newest. Each row is one recorded check.

  1. responds
    MCP initialize · 8s limit · HTTP 200 · 26ms
  2. responds
    MCP initialize · 8s limit · HTTP 200 · 245ms
  3. responds
    MCP initialize · 8s limit · HTTP 200 · 207ms
  4. responds
    MCP initialize · 8s limit · HTTP 200 · 898ms
Back to MCP directory