{"data":{"name":"com.brainiall/pronunciation","title":"Brainiall Pronunciation","description":"Pronunciation assessment, phoneme scoring, speaker voice ID, audio transcription, speech synthesis.","version":"1.0.0","websiteUrl":"https://brainiall.com","repositoryUrl":null,"remotes":[{"url":"https://api.brainiall.com/mcp/pronunciation/mcp","type":"streamable-http"}],"packages":[],"status":"active","isLatest":true,"publishedAt":"2026-08-26T19:02:39.191Z","updatedAt":"2026-08-26T19:02:39.191Z","source":"official-registry","verification":"official","confidence":100,"stars":null,"sources":[{"stars":null,"title":"Brainiall Pronunciation","source":"official-registry","sourceId":"com.brainiall/pronunciation","updatedAt":"2026-08-26T19:02:39.191Z","confidence":100,"websiteUrl":"https://brainiall.com","description":"Pronunciation assessment, phoneme scoring, speaker voice ID, audio transcription, speech synthesis.","verification":"official","repositoryUrl":null}],"toolIndex":{"tools":[{"serverName":"com.brainiall/pronunciation","endpointFingerprint":"615cace831ce529a77f365249999513e949a4ffb284b117e3f900046f1ae72f1","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":"2026-11-15T02:46:14.216Z","metadataTrust":"untrusted"},{"serverName":"com.brainiall/pronunciation","endpointFingerprint":"615cace831ce529a77f365249999513e949a4ffb284b117e3f900046f1ae72f1","name":"check_pronunciation_service","title":"Check Pronunciation Service","description":"Check if the Brainiall Pronunciation 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":"3bddc91694e5d982e6fa6be6589fb018de8c58e17e4e70f74dcec713411d2ad2","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-15T02:46:14.216Z","metadataTrust":"untrusted"},{"serverName":"com.brainiall/pronunciation","endpointFingerprint":"615cace831ce529a77f365249999513e949a4ffb284b117e3f900046f1ae72f1","name":"check_stt_service","title":"Check STT Service","description":"Check if the Brainiall Speech service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded (bool): Whether the speech-recognition 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":"022890a0edd968ff347162e5e41d6700359683f77c5a527c403b3057ec81078e","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-15T02:46:14.216Z","metadataTrust":"untrusted"},{"serverName":"com.brainiall/pronunciation","endpointFingerprint":"615cace831ce529a77f365249999513e949a4ffb284b117e3f900046f1ae72f1","name":"check_tts_service","title":"Check TTS Service","description":"Check if the Brainiall Voice service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded (bool): Whether the synthesis 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":"6d9f8c91f605743aece34ded9a3fc3a28aef0232253422062caa1022d83879a2","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-15T02:46:14.216Z","metadataTrust":"untrusted"},{"serverName":"com.brainiall/pronunciation","endpointFingerprint":"615cace831ce529a77f365249999513e949a4ffb284b117e3f900046f1ae72f1","name":"check_whisper_service","title":"Check Brainiall Speech Pro Service","description":"Check if the Brainiall Speech Pro service is healthy and ready.\n\nReturns:\n    dict with keys:\n        - status (str): 'healthy' or error state\n        - modelLoaded (bool): Whether the Brainiall Speech Pro engine is loaded\n        - diarizeLoaded (bool): Whether the diarization pipeline is loaded\n        - version (str): API version\n        - modelName (str): Engine version identifier","inputSchema":{"type":"object","properties":{}},"annotations":{"title":"Check Brainiall Speech Pro Service","readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true},"definitionHash":"e02e1c182a7ce2a436a4191579c2b1a5c67779df0ded0afe8c3c36a718753829","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-15T02:46:14.216Z","metadataTrust":"untrusted"},{"serverName":"com.brainiall/pronunciation","endpointFingerprint":"615cace831ce529a77f365249999513e949a4ffb284b117e3f900046f1ae72f1","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":"2026-11-15T02:46:14.216Z","metadataTrust":"untrusted"},{"serverName":"com.brainiall/pronunciation","endpointFingerprint":"615cace831ce529a77f365249999513e949a4ffb284b117e3f900046f1ae72f1","name":"list_tts_voices","title":"List TTS Voices","description":"List all available Brainiall Voice synthesis 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":"456a5a92feebe09b7f10fccf39c09f06881f306610ed92a693f27826f8e1d1f6","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-15T02:46:14.216Z","metadataTrust":"untrusted"},{"serverName":"com.brainiall/pronunciation","endpointFingerprint":"615cace831ce529a77f365249999513e949a4ffb284b117e3f900046f1ae72f1","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":"2026-11-15T02:46:14.216Z","metadataTrust":"untrusted"},{"serverName":"com.brainiall/pronunciation","endpointFingerprint":"615cace831ce529a77f365249999513e949a4ffb284b117e3f900046f1ae72f1","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":"2026-11-15T02:46:14.216Z","metadataTrust":"untrusted"},{"serverName":"com.brainiall/pronunciation","endpointFingerprint":"615cace831ce529a77f365249999513e949a4ffb284b117e3f900046f1ae72f1","name":"transcribe_audio_pro","title":"Transcribe Audio Pro","description":"Transcribe audio with Brainiall Speech Pro — multilingual transcription.\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","readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true},"definitionHash":"932b51f7c80ad81c0ad40edfbf73dfa94fe70f09a0b16dc6e8d16ab43730da14","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-15T02:46:14.216Z","metadataTrust":"untrusted"},{"serverName":"com.brainiall/pronunciation","endpointFingerprint":"615cace831ce529a77f365249999513e949a4ffb284b117e3f900046f1ae72f1","name":"voice_id_enroll","title":"Enroll Voiceprint","description":"Enroll a voiceprint for a speaker from ~2s of clear speech. Repeat with more clips to strengthen it.\n\nOnly an irreversible embedding is stored — never the raw audio.\n\nReturns:\n    dict with keys: speaker_id (str), n_samples (int), enrolled (bool).","inputSchema":{"type":"object","properties":{"audio":{"description":"Base64-encoded WAV with >= 2s of clear speech","type":"string"},"speaker_id":{"description":"Your identifier for this speaker","maxLength":256,"type":"string"},"group_id":{"description":"The group/namespace this speaker belongs to","maxLength":256,"type":"string"}},"required":["audio","speaker_id","group_id"]},"annotations":{"title":"Enroll Voiceprint","readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true},"definitionHash":"71a5a6abc8913e095d842905e480d0744bc839e8f144d9e995bfea5baa6dfdca","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-15T02:46:14.216Z","metadataTrust":"untrusted"},{"serverName":"com.brainiall/pronunciation","endpointFingerprint":"615cace831ce529a77f365249999513e949a4ffb284b117e3f900046f1ae72f1","name":"voice_id_identify","title":"Identify Speaker (1:N)","description":"1:N identification — rank everyone enrolled in the group against this clip.\n\nReturns:\n    dict with keys: candidates (list of {speaker_id, similarity}, best first).","inputSchema":{"type":"object","properties":{"audio":{"description":"Base64-encoded WAV of the clip to identify","type":"string"},"group_id":{"description":"The group/namespace to search within","maxLength":256,"type":"string"},"top_k":{"default":5,"description":"How many candidate speakers to return","maximum":50,"minimum":1,"type":"integer"}},"required":["audio","group_id"]},"annotations":{"title":"Identify Speaker (1:N)","readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true},"definitionHash":"d8eeff0e7398c9df80714e6b370c250549ec651f6b1a1b1362c8468a9259d477","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-15T02:46:14.216Z","metadataTrust":"untrusted"},{"serverName":"com.brainiall/pronunciation","endpointFingerprint":"615cace831ce529a77f365249999513e949a4ffb284b117e3f900046f1ae72f1","name":"voice_id_list_speakers","title":"List Enrolled Speakers","description":"List the speakers enrolled in a group.\n\nReturns:\n    dict with keys: speakers (list of {speaker_id, n_samples, ...}).","inputSchema":{"type":"object","properties":{"group_id":{"description":"The group/namespace to list","maxLength":256,"type":"string"}},"required":["group_id"]},"annotations":{"title":"List Enrolled Speakers","readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true},"definitionHash":"8056559f30873393cf7d27d2ae73820d0998aa425e5a3c105628481a0ace2a6e","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-15T02:46:14.216Z","metadataTrust":"untrusted"},{"serverName":"com.brainiall/pronunciation","endpointFingerprint":"615cace831ce529a77f365249999513e949a4ffb284b117e3f900046f1ae72f1","name":"voice_id_verify","title":"Verify Speaker (1:1)","description":"1:1 verification — is this clip the enrolled speaker?\n\nReturns:\n    dict with keys: similarity (float), match (bool), threshold (float).","inputSchema":{"type":"object","properties":{"audio":{"description":"Base64-encoded WAV of the clip to check","type":"string"},"speaker_id":{"description":"The enrolled speaker to verify against","maxLength":256,"type":"string"},"group_id":{"description":"The group/namespace","maxLength":256,"type":"string"},"threshold":{"anyOf":[{"type":"number"},{"type":"null"}],"default":null,"description":"Optional cosine-similarity threshold (defaults to a tuned value); higher = stricter"}},"required":["audio","speaker_id","group_id"]},"annotations":{"title":"Verify Speaker (1:1)","readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true},"definitionHash":"028577287898ab877ff99bda3683832427122cade0c7e6ea260efcc136d78a9e","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-15T02:46:14.216Z","metadataTrust":"untrusted"}],"endpoints":[{"endpointFingerprint":"615cace831ce529a77f365249999513e949a4ffb284b117e3f900046f1ae72f1","protocol":"streamable-http","status":"indexed","toolCount":14,"observedAt":"2026-11-15T02:46:14.216Z"}],"authentication":"unknown"},"connectionConfigurations":{"status":"ready","authentication":"not embedded","clients":{"Claude Desktop":{"mcpServers":{"com.brainiall/pronunciation":{"url":"https://api.brainiall.com/mcp/pronunciation/mcp"}}},"Cursor":{"mcpServers":{"com.brainiall/pronunciation":{"url":"https://api.brainiall.com/mcp/pronunciation/mcp"}}},"VS Code":{"servers":{"com.brainiall/pronunciation":{"type":"http","url":"https://api.brainiall.com/mcp/pronunciation/mcp"}}}}},"resourceType":"mcp-server","callable":true,"runtime":{"callable":true,"protocols":["mcp"]},"interfaces":[{"protocol":"mcp","transport":"streamable-http","url":"https://api.brainiall.com/mcp/pronunciation/mcp"}],"profile":{"apiVersion":"1","schemaVersion":"1","id":"mcp-server:com.brainiall%2Fpronunciation","resourceType":"mcp-server","canonicalUrl":"https://www.agentsjunction.com/api/v1/servers/com.brainiall%2Fpronunciation","name":"com.brainiall/pronunciation","description":"Pronunciation assessment, phoneme scoring, speaker voice ID, audio transcription, speech synthesis.","interfaces":[{"protocol":"mcp","transport":"streamable-http","url":"https://api.brainiall.com/mcp/pronunciation/mcp"}],"capabilities":[],"identity":{"source":"official-registry","websiteUrl":"https://brainiall.com","repositoryUrl":null,"version":"1.0.0"},"verification":{"state":"official","confidence":100},"operations":{"resourceType":"mcp-server","name":"com.brainiall/pronunciation","status":"online","lastCheckedAt":"2026-11-20T06:16:35.312Z","lastSuccessfulCheck":"2026-11-20T06:16:35.312Z","latencyMs":123,"consecutiveFailures":0,"isStale":false,"checks":{"endpointReachable":true,"protocolValid":true,"agentCardValid":null,"mcpHandshakeValid":true},"lastSeen":null,"lastSuccessfulInteraction":null,"lastHealthCheck":"2026-11-20T06:16:35.312Z","source":{"type":"health-check","url":null},"observedAt":"2026-11-20T06:16:35.312Z"},"security":null,"timestamps":{"createdAt":"2026-08-26T19:02:39.191Z","updatedAt":"2026-08-26T19:02:39.191Z","observedAt":"2026-11-20T06:16:35.312Z"},"compatibility":{"serverVersion":"1.0.0","protocolVersions":[{"protocol":"mcp","version":null}]}}}}