{"data":{"name":"io.github.fasuizu-br/speech-ai","title":"Speech AI - Pronunciation, STT & TTS","description":"Pronunciation scoring, speech-to-text, and text-to-speech for language learning","version":"2.3.0","websiteUrl":"https://brainiall.com","repositoryUrl":"https://github.com/fasuizu-br/speech-ai-examples","remotes":[{"url":"https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp","type":"streamable-http"}],"packages":[],"status":"active","isLatest":true,"publishedAt":"2026-03-05T04:04:33.203Z","updatedAt":"2026-03-05T04:04:33.203Z","source":"official-registry","verification":"official","confidence":100,"stars":null,"sources":[{"stars":null,"title":"Speech AI - Pronunciation, STT & TTS","source":"official-registry","sourceId":"io.github.fasuizu-br/speech-ai","updatedAt":"2026-03-05T04:04:33.203Z","confidence":100,"websiteUrl":"https://brainiall.com","description":"Pronunciation scoring, speech-to-text, and text-to-speech for language learning","verification":"official","repositoryUrl":"https://github.com/fasuizu-br/speech-ai-examples"}],"toolIndex":{"tools":[{"serverName":"io.github.fasuizu-br/speech-ai","endpointFingerprint":"1e352011087d48914ed25b6696ffba5342f0888589b199311d6ea152929c526e","name":"assess_pronunciation","title":"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 returned in both IPA and ARPAbet notation.\nSub-300ms inference latency.\n\nArgs:\n    audio_base64: Base64-encoded audio data. Supports WAV, MP3, OGG, and WebM formats.\n    text: The reference English text that the speaker was expected to read aloud.\n    audio_format: Audio format hint — one of 'wav', 'mp3', 'ogg', 'webm'. Defaults to 'wav'.\n\nReturns:\n    dict with keys:\n        - overallScore (int 0-100): Overall pronunciation quality\n        - sentenceScore (int 0-100): Sentence-level fluency and accuracy\n        - words (list): Per-word scores, each containing:\n            - word (str): The word\n            - score (int 0-100): Word pronunciation score\n            - phonemes (list): Per-phoneme scores with IPA/ARPAbet notation\n        - decodedTranscript (str): What the model heard (ASR transcript)\n        - transcript (str): Reference text\n        - confidence (float 0-1): Scoring confidence\n        - warnings (list[str]): Quality warnings if any\n        - audioQuality (dict): Audio metrics (SNR, peak/RMS dB, etc.)","inputSchema":{"type":"object","properties":{"audio_base64":{"description":"Base64-encoded audio data. Supports WAV, MP3, OGG, and WebM formats.","maxLength":20000000,"type":"string"},"text":{"description":"The reference English text that the speaker was expected to read aloud.","maxLength":10000,"type":"string"},"audio_format":{"default":"wav","description":"Audio format hint — one of 'wav', 'mp3', 'ogg', 'webm'.","type":"string"}},"required":["audio_base64","text"]},"annotations":{"title":"Assess Pronunciation","readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true},"definitionHash":"b4552cc230313ffff293b5656b0e22c03454d7432ec87816fb3abcc1fd848d41","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T13:46:50.741Z","metadataTrust":"untrusted"},{"serverName":"io.github.fasuizu-br/speech-ai","endpointFingerprint":"1e352011087d48914ed25b6696ffba5342f0888589b199311d6ea152929c526e","name":"check_pronunciation_service","title":"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        - modelLoaded (bool): Whether the scoring model is loaded\n        - version (str): API version","inputSchema":{"type":"object","properties":{}},"annotations":{"title":"Check Pronunciation Service","readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true},"definitionHash":"9f0820fffe1609978b33e582ccee03d12e0c8026bcc9f3ca9689346a87af19ad","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T13:46:50.741Z","metadataTrust":"untrusted"},{"serverName":"io.github.fasuizu-br/speech-ai","endpointFingerprint":"1e352011087d48914ed25b6696ffba5342f0888589b199311d6ea152929c526e","name":"check_stt_service","title":"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 (bool): Whether the STT model is loaded\n        - version (str): API version","inputSchema":{"type":"object","properties":{}},"annotations":{"title":"Check STT Service","readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true},"definitionHash":"58fb520cbed2c56274a008fa44a163a83ea909866875d3df95cb4ec5ee302545","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T13:46:50.741Z","metadataTrust":"untrusted"},{"serverName":"io.github.fasuizu-br/speech-ai","endpointFingerprint":"1e352011087d48914ed25b6696ffba5342f0888589b199311d6ea152929c526e","name":"check_tts_service","title":"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 (bool): Whether the TTS model is loaded\n        - version (str): API version","inputSchema":{"type":"object","properties":{}},"annotations":{"title":"Check TTS Service","readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true},"definitionHash":"17526b912c37ca4beaecc1e21d8701f3af3797df09f8456819ad5fbee988cffb","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T13:46:50.741Z","metadataTrust":"untrusted"},{"serverName":"io.github.fasuizu-br/speech-ai","endpointFingerprint":"1e352011087d48914ed25b6696ffba5342f0888589b199311d6ea152929c526e","name":"check_whisper_service","title":"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 (bool): Whether the Whisper model is loaded\n        - diarizeLoaded (bool): Whether the diarization pipeline is loaded\n        - version (str): API version\n        - modelName (str): Whisper model name (e.g. 'large-v3-turbo')","inputSchema":{"type":"object","properties":{}},"annotations":{"title":"Check Whisper Service","readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true},"definitionHash":"4e87f8002c6c8b0ebc7eeaf284a9be76beaedf893e4a4981fd5569167814787d","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T13:46:50.741Z","metadataTrust":"untrusted"},{"serverName":"io.github.fasuizu-br/speech-ai","endpointFingerprint":"1e352011087d48914ed25b6696ffba5342f0888589b199311d6ea152929c526e","name":"get_phoneme_inventory","title":"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, IPA equivalent, example word, and phoneme category\n(vowel, consonant, diphthong).\n\nReturns:\n    list of dicts, each with keys:\n        - arpabet (str): ARPAbet symbol (e.g. 'AA', 'TH')\n        - ipa (str): IPA notation\n        - example (str): Example word containing the phoneme\n        - category (str): vowel, consonant, or diphthong","inputSchema":{"type":"object","properties":{}},"annotations":{"title":"Get Phoneme Inventory","readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"definitionHash":"0c85325df7bf0505376403959594cd9dc7aa5b9db5c8b8d2b5a503986c7ae6f4","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T13:46:50.741Z","metadataTrust":"untrusted"},{"serverName":"io.github.fasuizu-br/speech-ai","endpointFingerprint":"1e352011087d48914ed25b6696ffba5342f0888589b199311d6ea152929c526e","name":"list_tts_voices","title":"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, accent, grade\n        - defaultVoice (str): Default voice ID","inputSchema":{"type":"object","properties":{}},"annotations":{"title":"List TTS Voices","readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true},"definitionHash":"277fb1b3d3deea6a668138e7664985e6bd3fd7ff9b669b9caa95a4bff3ab6956","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T13:46:50.741Z","metadataTrust":"untrusted"},{"serverName":"io.github.fasuizu-br/speech-ai","endpointFingerprint":"1e352011087d48914ed25b6696ffba5342f0888589b199311d6ea152929c526e","name":"synthesize_speech","title":"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) along with metadata.\n\nAvailable voices:\n- af_heart (default), af_bella, af_nicole, af_sarah, af_sky (American female)\n- am_adam, am_michael (American male)\n- bf_emma, bf_isabella (British female)\n- bm_george, bm_lewis, bm_daniel (British male)\n\nArgs:\n    text: English text to synthesize (1-5000 characters).\n    voice: Voice ID. See list above. Defaults to 'af_heart'.\n    speed: Speed multiplier from 0.5 to 2.0 (default: 1.0).\n\nReturns:\n    dict with keys:\n        - audio_base64 (str): Base64-encoded WAV audio (16-bit PCM, 24kHz)\n        - duration_ms (str): Audio duration in milliseconds\n        - voice (str): Voice ID used\n        - text_length (str): Input text character count\n        - processing_ms (str): Synthesis time in milliseconds","inputSchema":{"type":"object","properties":{"text":{"description":"English text to convert to speech. Max 5000 characters.","maxLength":5000,"type":"string"},"voice":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"description":"Voice ID (e.g. 'af_heart', 'am_adam'). Uses default if omitted."},"speed":{"default":1,"description":"Speech speed multiplier (0.5 = half speed, 2.0 = double).","type":"number"}},"required":["text"]},"annotations":{"title":"Synthesize Speech","readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true},"definitionHash":"26cff83f1fda755af8d085973a02ae098b0587e4e5145ffc924e6ac48b51fd78","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T13:46:50.741Z","metadataTrust":"untrusted"},{"serverName":"io.github.fasuizu-br/speech-ai","endpointFingerprint":"1e352011087d48914ed25b6696ffba5342f0888589b199311d6ea152929c526e","name":"transcribe_audio","title":"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.\n\nArgs:\n    audio_base64: Base64-encoded audio data (WAV, MP3, OGG, FLAC, WebM).\n    audio_format: Audio format hint. Auto-detected from magic bytes if omitted.\n    include_timestamps: Whether to include word-level timing (default: true).\n\nReturns:\n    dict with keys:\n        - text (str): Full decoded transcript\n        - words (list): Per-word results with timestamps, each containing:\n            - word (str): The transcribed word\n            - start (float): Start time in seconds\n            - end (float): End time in seconds\n            - confidence (float 0-1): Word-level confidence\n        - audioDurationMs (int): Audio duration in milliseconds\n        - metadata (dict): Processing time, audio length, model version\n        - audioQuality (dict): Audio metrics (SNR, peak/RMS dB, etc.)","inputSchema":{"type":"object","properties":{"audio_base64":{"description":"Base64-encoded audio data. Supports WAV, MP3, OGG, FLAC, and WebM formats.","maxLength":20000000,"type":"string"},"audio_format":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"description":"Audio format hint — 'wav', 'mp3', 'ogg', 'flac', 'webm'. Auto-detected if omitted."},"include_timestamps":{"default":true,"description":"If true, include word-level start/end times and confidence.","type":"boolean"}},"required":["audio_base64"]},"annotations":{"title":"Transcribe Audio","readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true},"definitionHash":"f426671550b095be6ea622e4eeb9244c5fb743d97b68b80fca3b0e1dfe7947dd","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T13:46:50.741Z","metadataTrust":"untrusted"},{"serverName":"io.github.fasuizu-br/speech-ai","endpointFingerprint":"1e352011087d48914ed25b6696ffba5342f0888589b199311d6ea152929c526e","name":"transcribe_audio_pro","title":"Transcribe Audio Pro (Whisper)","description":"Transcribe audio with Whisper Large V3 Turbo — multilingual STT.\n\nSupports 99 languages with automatic language detection, word-level\ntimestamps, per-word confidence scores, and optional speaker diarization\n(identifies who spoke each word). Best-in-class WER (~2%).\n\nArgs:\n    audio_base64: Base64-encoded audio (WAV, MP3, OGG, FLAC, WebM).\n    language: Language code. Auto-detected if omitted. Supports 99 languages.\n    diarize: Enable speaker diarization (default: false). When true, each word\n        includes a speaker label (e.g. SPEAKER_00, SPEAKER_01).\n\nReturns:\n    dict with keys:\n        - text (str): Full decoded transcript\n        - words (list): Per-word results with timestamps, each containing:\n            - word (str), start (float), end (float), confidence (float 0-1)\n            - speaker (str|null): Speaker label when diarize=true\n        - speakers (dict|null): Speaker info with count and labels\n        - audioDurationMs (int): Audio duration in milliseconds\n        - metadata (dict): Processing time, language, languageProbability\n        - audioQuality (dict): Audio metrics (SNR, peak/RMS dB, etc.)","inputSchema":{"type":"object","properties":{"audio_base64":{"description":"Base64-encoded audio data. Supports WAV, MP3, OGG, FLAC, and WebM formats.","maxLength":20000000,"type":"string"},"language":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"description":"Language code (e.g. 'en', 'es', 'zh'). Auto-detected when omitted."},"diarize":{"default":false,"description":"Enable speaker diarization to identify who spoke each word.","type":"boolean"}},"required":["audio_base64"]},"annotations":{"title":"Transcribe Audio Pro (Whisper)","readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true},"definitionHash":"f7ee84a63d6e30b5d16f9cfaad4afbb0b0fc2af60bc50a75f370fb751b8e892b","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T13:46:50.741Z","metadataTrust":"untrusted"}],"endpoints":[{"endpointFingerprint":"1e352011087d48914ed25b6696ffba5342f0888589b199311d6ea152929c526e","protocol":"streamable-http","status":"indexed","toolCount":10,"observedAt":"2026-11-19T13:46:50.741Z"}],"authentication":"unknown"},"connectionConfigurations":{"status":"ready","authentication":"not embedded","clients":{"Claude Desktop":{"mcpServers":{"io.github.fasuizu-br/speech-ai":{"url":"https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp"}}},"Cursor":{"mcpServers":{"io.github.fasuizu-br/speech-ai":{"url":"https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp"}}},"VS Code":{"servers":{"io.github.fasuizu-br/speech-ai":{"type":"http","url":"https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp"}}}}},"resourceType":"mcp-server","callable":true,"runtime":{"callable":true,"protocols":["mcp"]},"interfaces":[{"protocol":"mcp","transport":"streamable-http","url":"https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp"}],"profile":{"apiVersion":"1","schemaVersion":"1","id":"mcp-server:io.github.fasuizu-br%2Fspeech-ai","resourceType":"mcp-server","canonicalUrl":"https://www.agentsjunction.com/api/v1/servers/io.github.fasuizu-br%2Fspeech-ai","name":"io.github.fasuizu-br/speech-ai","description":"Pronunciation scoring, speech-to-text, and text-to-speech for language learning","interfaces":[{"protocol":"mcp","transport":"streamable-http","url":"https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp"}],"capabilities":[],"identity":{"source":"official-registry","websiteUrl":"https://brainiall.com","repositoryUrl":"https://github.com/fasuizu-br/speech-ai-examples","version":"2.3.0"},"verification":{"state":"official","confidence":100},"operations":{"resourceType":"mcp-server","name":"io.github.fasuizu-br/speech-ai","status":"degraded","lastCheckedAt":"2026-11-20T04:17:28.567Z","lastSuccessfulCheck":"2026-11-19T23:15:54.567Z","latencyMs":8001,"consecutiveFailures":1,"isStale":false,"checks":{"endpointReachable":false,"protocolValid":false,"agentCardValid":null,"mcpHandshakeValid":false},"lastSeen":null,"lastSuccessfulInteraction":null,"lastHealthCheck":"2026-11-20T04:17:28.567Z","source":{"type":"health-check","url":null},"observedAt":"2026-11-20T04:17:28.567Z"},"security":null,"timestamps":{"createdAt":"2026-03-05T04:04:33.203Z","updatedAt":"2026-03-05T04:04:33.203Z","observedAt":"2026-11-20T04:17:28.567Z"},"compatibility":{"serverVersion":"2.3.0","protocolVersions":[{"protocol":"mcp","version":null}]}}}}