{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_ysa5r3kzckqk","handle":"speech-ai-pronunciation-stt-tts","url":"https://wellknown.network/agents/speech-ai-pronunciation-stt-tts","links":{"self":"https://wellknown.network/agents/speech-ai-pronunciation-stt-tts/record.json","html":"https://wellknown.network/agents/speech-ai-pronunciation-stt-tts","markdown":"https://wellknown.network/agents/speech-ai-pronunciation-stt-tts/record.md","api":"https://wellknown.network/api/v1/agents/speech-ai-pronunciation-stt-tts","status":"https://wellknown.network/api/v1/agents/speech-ai-pronunciation-stt-tts/status","claim":"https://wellknown.network/agents/speech-ai-pronunciation-stt-tts/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/speech-ai-pronunciation-stt-tts/claim.json","badge":"https://wellknown.network/agents/speech-ai-pronunciation-stt-tts/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/speech-ai-pronunciation-stt-tts/history","tools":"https://wellknown.network/api/v1/agents/speech-ai-pronunciation-stt-tts/tools"},"ard":{"identifier":"urn:air:apim-ai-apis.azure-api.net:server:speech-ai-pronunciation-stt-tts","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"Speech AI - Pronunciation, STT & TTS","summary":"Pronunciation scoring, speech-to-text, and text-to-speech for language learning","description":"Pronunciation scoring, speech-to-text, and text-to-speech for language learning","publisher":{"name":"fasuizu-br","url":null},"homepage":"https://brainiall.com","repository":"https://github.com/fasuizu-br/speech-ai-examples","version":"2.3.0","license":null,"protocols":["mcp"],"tags":[],"pricing":null,"endpoints":[{"url":"https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp","type":"mcp_streamable_http","auth":null,"probeable":true}],"skills":null,"tools":null,"extra":{"updatedAt":"2026-03-05T04:04:33.203328Z","publishedAt":"2026-03-05T04:04:33.203328Z","registryName":"io.github.fasuizu-br/speech-ai"},"attribution":{"kind":"mcp_registry","name":"mcp_registry","repoUrl":"mcp_registry","summary":"mcp_registry","version":"mcp_registry","description":"mcp_registry","homepageUrl":"mcp_registry","publisherName":"mcp_registry"}},"derived":{"capabilities":[{"slug":"media.speech-synthesis","name":"Speech Synthesis","confidence":1,"provenance":"derived"},{"slug":"media.speech-recognition","name":"Speech Recognition","confidence":1,"provenance":"derived"},{"slug":"content.translation","name":"Translation","confidence":0.583,"provenance":"derived"},{"slug":"commerce.ecommerce","name":"E-commerce Operations","confidence":0.54,"provenance":"derived"},{"slug":"documents.conversion","name":"Document Conversion","confidence":0.51,"provenance":"derived"}],"categories":["commerce","content","documents","media"],"language":"en"},"observed":{"status":"live","statusReason":"Responded 5h ago.","lastOkAt":"2026-10-10T13:26:14.879Z","lastProbedAt":"2026-10-10T13:26:14.879Z","statusComputedAt":"2026-10-10T13:26:53.984Z","reliability30d":{"probes":54,"successRate":0.9259,"p50Ms":127,"basis":"service","measures":{"availability":"availability","latency":"response time","tools":"tool surface observed","summary":"Checks reached the service itself."},"checks":{"total":54,"ok":50,"authBoundaryOk":0,"serviceOk":50,"note":"Counted from the observation rows for the window, checks of the server only (HTTP, A2A card, MCP initialize). ok = authBoundaryOk + serviceOk. `probes` is the sum of daily rollups and includes registry checks, so it can differ from `total`."}},"latestObservations":[{"at":"2026-10-10T13:26:14.879Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":116,"error":null,"detail":{"tools":[{"name":"assess_pronunciation","description":"Assess English pronunciation quality from audio.\n\nScores pronunciation at four levels: overall, sentence, word, and phoneme.\nEach score is 0-100. Phonemes are r"},{"name":"check_pronunciation_service","description":"Check if the pronunciation assessment service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - mod"},{"name":"get_phoneme_inventory","description":"Get the full phoneme inventory supported by the pronunciation scorer.\n\nReturns a list of all English phonemes the engine can assess, including\nARPAbet symbol, I"},{"name":"transcribe_audio","description":"Transcribe audio to text with word-level timestamps.\n\nConverts spoken English audio into text with optional word-level timestamps\nand per-word confidence scores"},{"name":"check_stt_service","description":"Check if the speech-to-text service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded ("},{"name":"synthesize_speech","description":"Generate natural speech audio from English text.\n\nProduces high-quality speech with 12 English voices.\nReturns base64-encoded WAV audio (16-bit PCM, 24kHz mono)"},{"name":"list_tts_voices","description":"List all available text-to-speech voices with metadata.\n\nReturns:\n    dict with keys:\n        - voices (list): Available voices, each with id, name, gender, acc"},{"name":"check_tts_service","description":"Check if the text-to-speech service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded ("},{"name":"transcribe_audio_pro","description":"Transcribe audio with Whisper Large V3 Turbo — multilingual STT.\n\nSupports 99 languages with automatic language detection, word-level\ntimestamps, per-word confi"},{"name":"check_whisper_service","description":"Check if the Whisper STT Pro service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded "}],"toolCount":10,"toolsHash":"c33eec9f68ea780f3257ac6db6d0d79f3170c311c75f0caed9564e2ef6dad1ec","serverName":"speech-ai","capabilities":["experimental","prompts","resources","tools","tasks"],"serverVersion":"2.14.5","protocolVersion":"2025-06-18"}},{"at":"2026-10-10T07:25:06.521Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":116,"error":null,"detail":{"tools":[{"name":"assess_pronunciation","description":"Assess English pronunciation quality from audio.\n\nScores pronunciation at four levels: overall, sentence, word, and phoneme.\nEach score is 0-100. Phonemes are r"},{"name":"check_pronunciation_service","description":"Check if the pronunciation assessment service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - mod"},{"name":"get_phoneme_inventory","description":"Get the full phoneme inventory supported by the pronunciation scorer.\n\nReturns a list of all English phonemes the engine can assess, including\nARPAbet symbol, I"},{"name":"transcribe_audio","description":"Transcribe audio to text with word-level timestamps.\n\nConverts spoken English audio into text with optional word-level timestamps\nand per-word confidence scores"},{"name":"check_stt_service","description":"Check if the speech-to-text service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded ("},{"name":"synthesize_speech","description":"Generate natural speech audio from English text.\n\nProduces high-quality speech with 12 English voices.\nReturns base64-encoded WAV audio (16-bit PCM, 24kHz mono)"},{"name":"list_tts_voices","description":"List all available text-to-speech voices with metadata.\n\nReturns:\n    dict with keys:\n        - voices (list): Available voices, each with id, name, gender, acc"},{"name":"check_tts_service","description":"Check if the text-to-speech service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded ("},{"name":"transcribe_audio_pro","description":"Transcribe audio with Whisper Large V3 Turbo — multilingual STT.\n\nSupports 99 languages with automatic language detection, word-level\ntimestamps, per-word confi"},{"name":"check_whisper_service","description":"Check if the Whisper STT Pro service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded "}],"toolCount":10,"toolsHash":"c33eec9f68ea780f3257ac6db6d0d79f3170c311c75f0caed9564e2ef6dad1ec","serverName":"speech-ai","capabilities":["experimental","prompts","resources","tools","tasks"],"serverVersion":"2.14.5","protocolVersion":"2025-06-18"}},{"at":"2026-10-10T01:24:41.629Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":101,"error":null,"detail":{"tools":[{"name":"assess_pronunciation","description":"Assess English pronunciation quality from audio.\n\nScores pronunciation at four levels: overall, sentence, word, and phoneme.\nEach score is 0-100. Phonemes are r"},{"name":"check_pronunciation_service","description":"Check if the pronunciation assessment service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - mod"},{"name":"get_phoneme_inventory","description":"Get the full phoneme inventory supported by the pronunciation scorer.\n\nReturns a list of all English phonemes the engine can assess, including\nARPAbet symbol, I"},{"name":"transcribe_audio","description":"Transcribe audio to text with word-level timestamps.\n\nConverts spoken English audio into text with optional word-level timestamps\nand per-word confidence scores"},{"name":"check_stt_service","description":"Check if the speech-to-text service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded ("},{"name":"synthesize_speech","description":"Generate natural speech audio from English text.\n\nProduces high-quality speech with 12 English voices.\nReturns base64-encoded WAV audio (16-bit PCM, 24kHz mono)"},{"name":"list_tts_voices","description":"List all available text-to-speech voices with metadata.\n\nReturns:\n    dict with keys:\n        - voices (list): Available voices, each with id, name, gender, acc"},{"name":"check_tts_service","description":"Check if the text-to-speech service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded ("},{"name":"transcribe_audio_pro","description":"Transcribe audio with Whisper Large V3 Turbo — multilingual STT.\n\nSupports 99 languages with automatic language detection, word-level\ntimestamps, per-word confi"},{"name":"check_whisper_service","description":"Check if the Whisper STT Pro service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded "}],"toolCount":10,"toolsHash":"c33eec9f68ea780f3257ac6db6d0d79f3170c311c75f0caed9564e2ef6dad1ec","serverName":"speech-ai","capabilities":["experimental","prompts","resources","tools","tasks"],"serverVersion":"2.14.5","protocolVersion":"2025-06-18"}},{"at":"2026-10-09T19:27:14.651Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":115,"error":null,"detail":{"tools":[{"name":"assess_pronunciation","description":"Assess English pronunciation quality from audio.\n\nScores pronunciation at four levels: overall, sentence, word, and phoneme.\nEach score is 0-100. Phonemes are r"},{"name":"check_pronunciation_service","description":"Check if the pronunciation assessment service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - mod"},{"name":"get_phoneme_inventory","description":"Get the full phoneme inventory supported by the pronunciation scorer.\n\nReturns a list of all English phonemes the engine can assess, including\nARPAbet symbol, I"},{"name":"transcribe_audio","description":"Transcribe audio to text with word-level timestamps.\n\nConverts spoken English audio into text with optional word-level timestamps\nand per-word confidence scores"},{"name":"check_stt_service","description":"Check if the speech-to-text service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded ("},{"name":"synthesize_speech","description":"Generate natural speech audio from English text.\n\nProduces high-quality speech with 12 English voices.\nReturns base64-encoded WAV audio (16-bit PCM, 24kHz mono)"},{"name":"list_tts_voices","description":"List all available text-to-speech voices with metadata.\n\nReturns:\n    dict with keys:\n        - voices (list): Available voices, each with id, name, gender, acc"},{"name":"check_tts_service","description":"Check if the text-to-speech service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded ("},{"name":"transcribe_audio_pro","description":"Transcribe audio with Whisper Large V3 Turbo — multilingual STT.\n\nSupports 99 languages with automatic language detection, word-level\ntimestamps, per-word confi"},{"name":"check_whisper_service","description":"Check if the Whisper STT Pro service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded "}],"toolCount":10,"toolsHash":"c33eec9f68ea780f3257ac6db6d0d79f3170c311c75f0caed9564e2ef6dad1ec","serverName":"speech-ai","capabilities":["experimental","prompts","resources","tools","tasks"],"serverVersion":"2.14.5","protocolVersion":"2025-06-18"}},{"at":"2026-10-09T13:29:45.966Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":117,"error":null,"detail":{"tools":[{"name":"assess_pronunciation","description":"Assess English pronunciation quality from audio.\n\nScores pronunciation at four levels: overall, sentence, word, and phoneme.\nEach score is 0-100. Phonemes are r"},{"name":"check_pronunciation_service","description":"Check if the pronunciation assessment service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - mod"},{"name":"get_phoneme_inventory","description":"Get the full phoneme inventory supported by the pronunciation scorer.\n\nReturns a list of all English phonemes the engine can assess, including\nARPAbet symbol, I"},{"name":"transcribe_audio","description":"Transcribe audio to text with word-level timestamps.\n\nConverts spoken English audio into text with optional word-level timestamps\nand per-word confidence scores"},{"name":"check_stt_service","description":"Check if the speech-to-text service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded ("},{"name":"synthesize_speech","description":"Generate natural speech audio from English text.\n\nProduces high-quality speech with 12 English voices.\nReturns base64-encoded WAV audio (16-bit PCM, 24kHz mono)"},{"name":"list_tts_voices","description":"List all available text-to-speech voices with metadata.\n\nReturns:\n    dict with keys:\n        - voices (list): Available voices, each with id, name, gender, acc"},{"name":"check_tts_service","description":"Check if the text-to-speech service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded ("},{"name":"transcribe_audio_pro","description":"Transcribe audio with Whisper Large V3 Turbo — multilingual STT.\n\nSupports 99 languages with automatic language detection, word-level\ntimestamps, per-word confi"},{"name":"check_whisper_service","description":"Check if the Whisper STT Pro service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded "}],"toolCount":10,"toolsHash":"c33eec9f68ea780f3257ac6db6d0d79f3170c311c75f0caed9564e2ef6dad1ec","serverName":"speech-ai","capabilities":["experimental","prompts","resources","tools","tasks"],"serverVersion":"2.14.5","protocolVersion":"2025-06-18"}},{"at":"2026-10-09T06:22:04.996Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":286,"error":null,"detail":{"tools":[{"name":"assess_pronunciation","description":"Assess English pronunciation quality from audio.\n\nScores pronunciation at four levels: overall, sentence, word, and phoneme.\nEach score is 0-100. Phonemes are r"},{"name":"check_pronunciation_service","description":"Check if the pronunciation assessment service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - mod"},{"name":"get_phoneme_inventory","description":"Get the full phoneme inventory supported by the pronunciation scorer.\n\nReturns a list of all English phonemes the engine can assess, including\nARPAbet symbol, I"},{"name":"transcribe_audio","description":"Transcribe audio to text with word-level timestamps.\n\nConverts spoken English audio into text with optional word-level timestamps\nand per-word confidence scores"},{"name":"check_stt_service","description":"Check if the speech-to-text service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded ("},{"name":"synthesize_speech","description":"Generate natural speech audio from English text.\n\nProduces high-quality speech with 12 English voices.\nReturns base64-encoded WAV audio (16-bit PCM, 24kHz mono)"},{"name":"list_tts_voices","description":"List all available text-to-speech voices with metadata.\n\nReturns:\n    dict with keys:\n        - voices (list): Available voices, each with id, name, gender, acc"},{"name":"check_tts_service","description":"Check if the text-to-speech service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded ("},{"name":"transcribe_audio_pro","description":"Transcribe audio with Whisper Large V3 Turbo — multilingual STT.\n\nSupports 99 languages with automatic language detection, word-level\ntimestamps, per-word confi"},{"name":"check_whisper_service","description":"Check if the Whisper STT Pro service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded "}],"toolCount":10,"toolsHash":"c33eec9f68ea780f3257ac6db6d0d79f3170c311c75f0caed9564e2ef6dad1ec","serverName":"speech-ai","capabilities":["experimental","prompts","resources","tools","tasks"],"serverVersion":"2.14.5","protocolVersion":"2025-06-18"}},{"at":"2026-10-09T00:24:20.387Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":177,"error":null,"detail":{"tools":[{"name":"assess_pronunciation","description":"Assess English pronunciation quality from audio.\n\nScores pronunciation at four levels: overall, sentence, word, and phoneme.\nEach score is 0-100. Phonemes are r"},{"name":"check_pronunciation_service","description":"Check if the pronunciation assessment service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - mod"},{"name":"get_phoneme_inventory","description":"Get the full phoneme inventory supported by the pronunciation scorer.\n\nReturns a list of all English phonemes the engine can assess, including\nARPAbet symbol, I"},{"name":"transcribe_audio","description":"Transcribe audio to text with word-level timestamps.\n\nConverts spoken English audio into text with optional word-level timestamps\nand per-word confidence scores"},{"name":"check_stt_service","description":"Check if the speech-to-text service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded ("},{"name":"synthesize_speech","description":"Generate natural speech audio from English text.\n\nProduces high-quality speech with 12 English voices.\nReturns base64-encoded WAV audio (16-bit PCM, 24kHz mono)"},{"name":"list_tts_voices","description":"List all available text-to-speech voices with metadata.\n\nReturns:\n    dict with keys:\n        - voices (list): Available voices, each with id, name, gender, acc"},{"name":"check_tts_service","description":"Check if the text-to-speech service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded ("},{"name":"transcribe_audio_pro","description":"Transcribe audio with Whisper Large V3 Turbo — multilingual STT.\n\nSupports 99 languages with automatic language detection, word-level\ntimestamps, per-word confi"},{"name":"check_whisper_service","description":"Check if the Whisper STT Pro service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded "}],"toolCount":10,"toolsHash":"c33eec9f68ea780f3257ac6db6d0d79f3170c311c75f0caed9564e2ef6dad1ec","serverName":"speech-ai","capabilities":["experimental","prompts","resources","tools","tasks"],"serverVersion":"2.14.5","protocolVersion":"2025-06-18"}},{"at":"2026-10-08T17:26:21.278Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":111,"error":null,"detail":{"tools":[{"name":"assess_pronunciation","description":"Assess English pronunciation quality from audio.\n\nScores pronunciation at four levels: overall, sentence, word, and phoneme.\nEach score is 0-100. Phonemes are r"},{"name":"check_pronunciation_service","description":"Check if the pronunciation assessment service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - mod"},{"name":"get_phoneme_inventory","description":"Get the full phoneme inventory supported by the pronunciation scorer.\n\nReturns a list of all English phonemes the engine can assess, including\nARPAbet symbol, I"},{"name":"transcribe_audio","description":"Transcribe audio to text with word-level timestamps.\n\nConverts spoken English audio into text with optional word-level timestamps\nand per-word confidence scores"},{"name":"check_stt_service","description":"Check if the speech-to-text service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded ("},{"name":"synthesize_speech","description":"Generate natural speech audio from English text.\n\nProduces high-quality speech with 12 English voices.\nReturns base64-encoded WAV audio (16-bit PCM, 24kHz mono)"},{"name":"list_tts_voices","description":"List all available text-to-speech voices with metadata.\n\nReturns:\n    dict with keys:\n        - voices (list): Available voices, each with id, name, gender, acc"},{"name":"check_tts_service","description":"Check if the text-to-speech service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded ("},{"name":"transcribe_audio_pro","description":"Transcribe audio with Whisper Large V3 Turbo — multilingual STT.\n\nSupports 99 languages with automatic language detection, word-level\ntimestamps, per-word confi"},{"name":"check_whisper_service","description":"Check if the Whisper STT Pro service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded "}],"toolCount":10,"toolsHash":"c33eec9f68ea780f3257ac6db6d0d79f3170c311c75f0caed9564e2ef6dad1ec","serverName":"speech-ai","capabilities":["experimental","prompts","resources","tools","tasks"],"serverVersion":"2.14.5","protocolVersion":"2025-06-18"}},{"at":"2026-10-08T10:22:47.773Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":105,"error":null,"detail":{"tools":[{"name":"assess_pronunciation","description":"Assess English pronunciation quality from audio.\n\nScores pronunciation at four levels: overall, sentence, word, and phoneme.\nEach score is 0-100. Phonemes are r"},{"name":"check_pronunciation_service","description":"Check if the pronunciation assessment service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - mod"},{"name":"get_phoneme_inventory","description":"Get the full phoneme inventory supported by the pronunciation scorer.\n\nReturns a list of all English phonemes the engine can assess, including\nARPAbet symbol, I"},{"name":"transcribe_audio","description":"Transcribe audio to text with word-level timestamps.\n\nConverts spoken English audio into text with optional word-level timestamps\nand per-word confidence scores"},{"name":"check_stt_service","description":"Check if the speech-to-text service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded ("},{"name":"synthesize_speech","description":"Generate natural speech audio from English text.\n\nProduces high-quality speech with 12 English voices.\nReturns base64-encoded WAV audio (16-bit PCM, 24kHz mono)"},{"name":"list_tts_voices","description":"List all available text-to-speech voices with metadata.\n\nReturns:\n    dict with keys:\n        - voices (list): Available voices, each with id, name, gender, acc"},{"name":"check_tts_service","description":"Check if the text-to-speech service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded ("},{"name":"transcribe_audio_pro","description":"Transcribe audio with Whisper Large V3 Turbo — multilingual STT.\n\nSupports 99 languages with automatic language detection, word-level\ntimestamps, per-word confi"},{"name":"check_whisper_service","description":"Check if the Whisper STT Pro service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded "}],"toolCount":10,"toolsHash":"c33eec9f68ea780f3257ac6db6d0d79f3170c311c75f0caed9564e2ef6dad1ec","serverName":"speech-ai","capabilities":["experimental","prompts","resources","tools","tasks"],"serverVersion":"2.14.5","protocolVersion":"2025-06-18"}},{"at":"2026-10-08T03:23:31.007Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":113,"error":null,"detail":{"tools":[{"name":"assess_pronunciation","description":"Assess English pronunciation quality from audio.\n\nScores pronunciation at four levels: overall, sentence, word, and phoneme.\nEach score is 0-100. Phonemes are r"},{"name":"check_pronunciation_service","description":"Check if the pronunciation assessment service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - mod"},{"name":"get_phoneme_inventory","description":"Get the full phoneme inventory supported by the pronunciation scorer.\n\nReturns a list of all English phonemes the engine can assess, including\nARPAbet symbol, I"},{"name":"transcribe_audio","description":"Transcribe audio to text with word-level timestamps.\n\nConverts spoken English audio into text with optional word-level timestamps\nand per-word confidence scores"},{"name":"check_stt_service","description":"Check if the speech-to-text service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded ("},{"name":"synthesize_speech","description":"Generate natural speech audio from English text.\n\nProduces high-quality speech with 12 English voices.\nReturns base64-encoded WAV audio (16-bit PCM, 24kHz mono)"},{"name":"list_tts_voices","description":"List all available text-to-speech voices with metadata.\n\nReturns:\n    dict with keys:\n        - voices (list): Available voices, each with id, name, gender, acc"},{"name":"check_tts_service","description":"Check if the text-to-speech service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded ("},{"name":"transcribe_audio_pro","description":"Transcribe audio with Whisper Large V3 Turbo — multilingual STT.\n\nSupports 99 languages with automatic language detection, word-level\ntimestamps, per-word confi"},{"name":"check_whisper_service","description":"Check if the Whisper STT Pro service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded "}],"toolCount":10,"toolsHash":"c33eec9f68ea780f3257ac6db6d0d79f3170c311c75f0caed9564e2ef6dad1ec","serverName":"speech-ai","capabilities":["experimental","prompts","resources","tools","tasks"],"serverVersion":"2.14.5","protocolVersion":"2025-06-18"}}],"tools":[{"name":"assess_pronunciation","description":"Assess English pronunciation quality from audio.\n\nScores pronunciation at four levels: overall, sentence, word, and phoneme.\nEach score is 0-100. Phonemes are r"},{"name":"check_pronunciation_service","description":"Check if the pronunciation assessment service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - mod"},{"name":"get_phoneme_inventory","description":"Get the full phoneme inventory supported by the pronunciation scorer.\n\nReturns a list of all English phonemes the engine can assess, including\nARPAbet symbol, I"},{"name":"transcribe_audio","description":"Transcribe audio to text with word-level timestamps.\n\nConverts spoken English audio into text with optional word-level timestamps\nand per-word confidence scores"},{"name":"check_stt_service","description":"Check if the speech-to-text service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded ("},{"name":"synthesize_speech","description":"Generate natural speech audio from English text.\n\nProduces high-quality speech with 12 English voices.\nReturns base64-encoded WAV audio (16-bit PCM, 24kHz mono)"},{"name":"list_tts_voices","description":"List all available text-to-speech voices with metadata.\n\nReturns:\n    dict with keys:\n        - voices (list): Available voices, each with id, name, gender, acc"},{"name":"check_tts_service","description":"Check if the text-to-speech service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded ("},{"name":"transcribe_audio_pro","description":"Transcribe audio with Whisper Large V3 Turbo — multilingual STT.\n\nSupports 99 languages with automatic language detection, word-level\ntimestamps, per-word confi"},{"name":"check_whisper_service","description":"Check if the Whisper STT Pro service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded "}],"package":null,"toolSurface":{"id":"ts_a9yggw4ugb9r","endpointId":"ep_vkeuvb3cevbv","hash":"c33eec9f68ea780f3257ac6db6d0d79f3170c311c75f0caed9564e2ef6dad1ec","toolCount":10,"serverName":"speech-ai","serverVersion":"2.14.5","protocolVersion":"2025-06-18","firstSeenAt":"2026-09-12T12:25:54.421Z","lastSeenAt":"2026-10-10T13:26:14.879Z","observations":92,"toolNames":["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"],"distinctSurfaces":1},"endpointFacts":[{"id":"ep_vkeuvb3cevbv","url":"https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp","type":"mcp_streamable_http","factsCheckedAt":"2026-10-09T13:29:45.980Z","auth":{"observedAt":"2026-10-09T13:29:46.335Z","authRequired":false,"scheme":null,"resourceMetadata":{"url":"https://apim-ai-apis.azure-api.net/.well-known/oauth-protected-resource/mcp/pronunciation/mcp","resource":"https://api.brainiall.com","authorizationServers":[],"scopesSupported":[]},"authorizationServer":null,"conformance":{"dpop":false,"rfc8414":false,"rfc9728":true,"pkceS256":false,"clientIdMetadataDocument":false,"dynamicClientRegistration":false}},"tls":{"observedAt":"2026-10-09T13:29:46.621Z","protocol":"TLSv1.3","chainValid":true,"chainError":null,"hostMatches":true,"subject":"*.azure-api.net","issuer":{"commonName":"Microsoft TLS G2 RSA CA OCSP 02","organization":"Microsoft Corporation"},"validFrom":"2026-08-29T00:33:14.000Z","validTo":"2027-02-25T00:33:14.000Z","daysToExpiry":137,"sanCount":18,"fingerprint256":"89:26:2C:EA:6B:2B:92:9A:BD:06:9D:FD:41:9B:56:44:10:5E:3F:FB:0D:D1:5B:01:AB:8D:D0:94:98:49:45:EC"}}]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"mcp_registry","key":"io.github.fasuizu-br/speech-ai","url":"https://registry.modelcontextprotocol.io/v0/servers/io.github.fasuizu-br%2Fspeech-ai","firstSeenAt":"2026-09-06T14:17:55.675Z","fetchedAt":"2026-10-10T10:21:33.226Z","normalizedAt":"2026-10-10T10:21:33.226Z"}]},"firstSeenAt":"2026-09-06T14:17:55.675Z","updatedAt":"2026-10-10T13:28:04.548Z"}