vocametrix
@vocametrix/mcp-server
Vocametrix音声分析APIの公式Model Context Protocolサーバーです。
MCP互換のAIアシスタント(Claude Desktop、Cursor、Clineなど)から、臨床音声メトリクス、発音評価、音声文字起こし、AIを活用したセラピー計画作成へ直接アクセスできます。
クイックスタート
Claude Desktop
~/Library/Application Support/Claude/claude_desktop_config.json (macOS) または %APPDATA%\Claude\claude_desktop_config.json (Windows) に以下を追加してください:
{
"mcpServers": {
"vocametrix": {
"command": "npx",
"args": ["-y", "@vocametrix/mcp-server"],
"env": {
"VOCAMETRIX_API_KEY": "your-api-key-here"
}
}
}
}APIキーはvocametrix.com/registrationで取得してください。無料トライアル:5分間の分析が可能。
Related MCP server: elevenlabs-mcp
ツール
音声品質(音響)
ツール | 説明 |
| 音響音声品質指数 (AVQI) — 発声障害の全体的な重症度 |
| 発声障害重症度指数 (DSI) |
| ケプストラム・ピーク・プロミネンス — 息漏れ、嗄声 |
| 調波対雑音比 (マルチバンド) |
| 周期および振幅の摂動 |
| 音域プロファイル (VRP) |
| 2つの発話間の韻律類似度 |
高度な音声分析
ツール | 説明 |
| スペクトルチルト、スロープ、およびフォルマントエネルギー |
| フォルマント周波数 F1–F4 |
| S/Z発声比 |
| 声門対雑音励起 (GNE) |
| H1–H2 調波差 |
| 音響息漏れ指数 (ABI) |
| ダイナミックレンジおよび基本周波数の統計 |
音声と発音
ツール | 説明 |
| 音素レベルの発音スコアリング |
| 発音とピッチ分析の組み合わせ |
| 進捗状況を含むストリーミングASR文字起こし |
| テキスト読み上げ合成 (TTS) |
| 単語レベルのタイミングデータ付きTTS |
音響測定
ツール | 説明 |
| dB SPLおよび強度の統計 |
| 拡張ジュネーブ最小音響パラメータセット (eGeMAPS) |
| 音素の有無の検出 |
| 吃音の分類 |
AIエージェント
ツール | 説明 |
| 音声メトリクスの臨床的解釈 |
| パーソナライズされた音声/発話練習の生成 |
| セラピー用ターゲット単語リストの生成 |
| 会話型AI言語聴覚士 |
| フランス語テキスト → IPA音声記号変換 |
| スペル修正エージェント |
| 構文チェックエージェント |
| 語彙学習エージェント |
| 適応型練習生成 |
セラピー計画
ツール | 説明 |
| AIセラピー計画の生成 |
| セラピー計画生成状況のポーリング |
| 完成したセラピー計画の取得 |
| セラピー計画の承認 |
ワークフローツール
ツール | 説明 |
| AVQI + CPP + HNR + ジッター/シマー + スペクトルの並列実行 |
| WAVファイルフォルダの一括評価 |
| 生成 → ポーリング → 取得 → 承認フロー |
リソース
vocametrix://docs/api— APIクイックリファレンス(認証、レート制限、音声要件、エラーコード)vocametrix://thresholds/{metric}—avqi、dsi、cpp、hnr、jitter-shimmer、gneの臨床基準値
プロンプト
interpret_voice_assessment— 評価JSONから臨床SLPスタイルの解釈レポートを生成compare_pre_post_therapy— メトリクスごとの比較を含む、セラピー前後の定量的なナラティブgenerate_session_report— 発音評価データからSOAP形式の経過記録を作成
音声要件
フォーマット: WAV (16-bit PCM推奨)
母音持続課題: 3秒以上の /a/ 発声
連続発話課題: 5〜30秒の朗読
最小サンプリングレート: 16 kHz
環境変数
変数 | 必須 | 説明 |
| はい | Vocametrix APIキー |
開発
git clone https://github.com/pmarmaroli/vocametrix-mcp.git
cd vocametrix-mcp
npm install
npm run build
npm run inspector # Test with MCP Inspector関連プロジェクト
Vocametrixエコシステム:
📘 Vocametrix APIドキュメント — このMCPサーバーを支えるREST APIの完全リファレンス。
📐 OpenAPI 3.1仕様 — 48個すべてのエンドポイントの機械可読スキーマ。
🐍 vocametrix-python — Pythonから直接APIにアクセスするための公式Python SDK (
pip install vocametrix)。🟦 vocametrix-js — このMCPサーバーが内部で使用している公式TypeScript / JavaScript SDK (
npm install vocametrix)。
ライセンス
MIT — LICENSEを参照
Available Tools
39 toolsvocametrix_adapt_exerciseA
Adapt a speech therapy exercise to a specific learner profile (ADHD, dyslexia, dysgraphia, dyspraxia, Tourette, autism). Returns an HTML-formatted adapted version of the exercise with profile-specific tips.
Inputs: exerciseText (required), learnerProfile (required), includeTips.
vocametrix_approve_therapy_planA
Human-in-the-loop approval gate for generated therapy plans. Actions: 'approve' (locks and delivers plan), 'reject' (discards), 'modify' (requires feedback, re-generates). This action is irreversible — once approved, the plan is sent for delivery.
Inputs: sessionId (required), action (required), feedback.
vocametrix_assess_pronunciationA
Score pronunciation accuracy at phoneme level against a reference text. Returns accuracy, fluency, completeness, and prosody scores (0–100) plus per-word and per-phoneme breakdowns. Supports 30+ locales (en-US, fr-FR, de-DE, zh-CN, ar-SA, etc.). Audio should be a clear reading of the reference text.
Inputs: audioPath (required), referenceText (required), speakerLocale.
vocametrix_assess_pronunciation_with_pitchA
Pronunciation assessment enriched with per-word F0 (pitch) contours. In addition to accuracy/fluency/prosody scores, returns fundamental frequency (pitch) statistics for each word — useful for tonal language analysis and prosody coaching.
Inputs: audioPath (required), referenceText (required), speakerLocale.
vocametrix_batch_pronunciationA
Assess pronunciation for all WAV files in a folder against a common reference text. Returns a table (Markdown + JSON) with accuracy, fluency, completeness, and prosody scores per file. Files are processed sequentially to stay within rate limits. Useful for classroom assessments, research cohorts, and batch L2 evaluation.
Inputs: folderPath (required), referenceText (required), locale.
vocametrix_calculate_abiC
Calculate the Acoustic Breathiness Index (ABI) combining connected speech and sustained vowel. ABI aggregates CPPS, jitter, GNE approximation, HNR (6 kHz), H1-H2, shimmer, and period SD. Sensitive to the full spectrum from breathy to pressed phonation.
Inputs: connectedSpeechPath (required), sustainedVowelPath (required).
vocametrix_calculate_avqiA
Calculate the Acoustic Voice Quality Index (AVQI v2.03 or v3.01), a clinically validated dysphonia score. AVQI > 2.43 (French) / 2.97 (English) indicates dysphonia. Requires a sustained vowel recording (e.g. /a/ held for 3+ seconds). Connected speech is optional but improves accuracy.
Inputs: sustainedVowelPath (required), connectedSpeechPath, version.
vocametrix_calculate_cppA
Calculate Cepstral Peak Prominence (CPP) from a sustained vowel. Higher CPP = better voice quality. Typical normal CPP: 20–28 dB. Clinically sensitive to breathiness and hoarseness.
Inputs: sustainedVowelPath (required).
vocametrix_calculate_dsiB
Calculate the Dysphonia Severity Index (DSI). DSI > 1.6 = normal voice; DSI < –1.6 = severe dysphonia. Requires a sustained vowel WAV file plus voice-range parameters (MPT, F0 range, minimum intensity).
Inputs: sustainedVowelPath (required), mpt (required), maximumF0 (required), minimumIntensity (required), +3 more.
vocametrix_calculate_formantsA
Compute F1–F4 formant statistics (mean, SD, range, CV, IQR) from a sustained vowel with vowel-space stability and articulatory precision scores. Useful for dysarthria assessment, vowel space analysis, and cleft palate evaluation.
Inputs: sustainedVowelPath (required), patientAge (required), patientGender (required).
vocametrix_calculate_gneA
Calculate the Glottal-to-Noise Excitation (GNE) ratio from a sustained vowel. GNE ranges 0–1; values < 0.5 suggest increased noise (breathiness/hoarseness). Computed via native Praat algorithm for clinical reliability.
Inputs: sustainedVowelPath (required).
vocametrix_calculate_h1_h2A
Calculate the formant-corrected H1*–H2* voice source measure from a sustained vowel. H1*–H2* is sensitive to breathiness: positive values indicate breathy voice, negative values indicate pressed/tense voice. Normal range: −2 to +2 dB.
Inputs: sustainedVowelPath (required), patientGender.
vocametrix_calculate_hnrA
Calculate multi-band Harmonics-to-Noise Ratio (HNR) across frequency bands (80–8000 Hz) with age- and gender-specific norms. Higher HNR = cleaner voice. Normal HNR (500 Hz band): > 20 dB. Requires a sustained vowel.
Inputs: sustainedVowelPath (required), patientAge (required), patientGender (required).
vocametrix_calculate_jitter_shimmerA
Calculate jitter (period perturbation, PPQ5) and shimmer (amplitude perturbation) from a sustained vowel. Normal jitter < 1.04%; normal shimmer < 3.81 dB. Elevated values indicate irregular vibration — associated with dysphonia.
Inputs: sustainedVowelPath (required).
vocametrix_calculate_prosody_similarityA
Compare prosodic patterns between a model (reference) recording and a learner recording. Returns similarity scores for pitch contour, intensity, duration, and pause patterns. Useful for accent coaching, speech imitation training, and L2 pronunciation.
Inputs: modelPath (required), learnerPath (required).
vocametrix_calculate_spectralA
Extract advanced spectral measures from a sustained vowel: center of gravity, skewness/kurtosis, H1-H2 (breathiness indicator), H1-A1, H1-A3, LTAS slope and tilt, alpha ratio. Returns age/gender-normalized norms and voice pattern classification.
Inputs: sustainedVowelPath (required), patientAge (required), patientGender (required), version.
vocametrix_calculate_sz_ratioA
Calculate the S/Z phonation ratio (duration of sustained /s/ vs /z/). Normal ratio ≈ 1.0. Ratio > 1.4 suggests vocal fold pathology (the /z/ is shorter). Requires two separate recordings: one of sustained /s/ and one of sustained /z/.
Inputs: sFilePath (required), zFilePath (required), patientAge (required), patientGender, +1 more.
vocametrix_calculate_voice_dynamicsA
Compute intensity dynamics, pitch-intensity correlation, and composite scores for voice control, projection, stability, effort, and monotonicity. Useful for voice training, public speaking coaching, and vocal fatigue assessment.
Inputs: sustainedVowelPath (required), patientAge (required), patientGender.
vocametrix_calculate_voice_range_profileA
Calculate the Voice Range Profile (VRP / ambitus / glissando) from a glissando recording. Returns frequency range (lowest to highest pitch) and intensity range with age/gender interpretation. Useful for singers and voice rehabilitation assessment.
Inputs: glissandoPath (required), patientAge, patientGender.
vocametrix_chat_speech_therapistA
Expert speech therapy assistant providing role-based guidance. Adapts its answers depending on whether the user is a therapist (clinical detail), a patient (accessible explanation), or a parent/caregiver (practical home tips). Maintains conversation context via threadId for multi-turn dialogue.
Inputs: message (required), accountType (required), threadId (required).
vocametrix_check_syntaxA
Analyze text for grammar and syntax errors with severity classification (error/warning/info). Returns overall score, per-issue breakdown, corrected text, and readability statistics. Useful for evaluating written language samples in speech-language assessments.
Inputs: text (required), locale (required).
vocametrix_classify_stutteringA
Classify stuttering disfluency patterns in a speech recording (async, ~30–120 seconds). Returns disfluency types (repetitions, prolongations, blocks), severity score, and fluency rate. The tool polls the result automatically — no separate status call needed.
Inputs: audioPath (required), pollIntervalMs, timeoutMs.
vocametrix_convert_french_to_ipaA
Convert French words or phrases to International Phonetic Alphabet (IPA) transcription. Accepts a single string or an array of up to 20 words. Returns IPA transcription per word with optional syllable boundary marks.
Inputs: input (required), includeSyllableMarks.
vocametrix_detect_phonemesA
Detect phonemes in an audio recording using a deep-learning classifier. Returns phoneme labels with confidence scores. Currently supports French (fr) and Estonian (et) phoneme inventories.
Inputs: audioPath (required), language.
vocametrix_extract_egemapsA
Extract the full openSMILE eGeMAPSv02 feature set (88 acoustic features) from an audio file. Features include F0, jitter, shimmer, HNR, MFCCs, formants, spectral flux, and loudness. Commonly used as input to machine-learning voice pathology classifiers.
Inputs: audioPath (required).
vocametrix_full_therapy_workflowA
End-to-end therapy plan generation with automatic polling and human-in-the-loop approval. Generates a therapy plan from session data, polls until complete, and presents it for approval. Returns the approved plan or the pending plan awaiting your approval action. After reviewing, call vocametrix_approve_therapy_plan with 'approve', 'modify', or 'reject'.
Inputs: sessionMetadata (required), wav2vecOutput (required), patientAnamnesis, pollIntervalMs, +1 more.
vocametrix_full_voice_assessmentA
Run a comprehensive clinical voice assessment in a single call. Executes AVQI, CPP, multi-band HNR, jitter/shimmer, and spectral analysis in parallel, then returns a unified JSON report with all metrics and clinical severity interpretation. Requires both a sustained vowel recording (e.g. /a/ held 3+ s) and a connected speech recording. This is the tool an SLP would use for a full voice quality screening.
Inputs: sustainedVowelPath (required), connectedSpeechPath (required), patientAge (required), patientGender (required).
vocametrix_generate_exercisesA
Generate personalized speech therapy exercises tailored to patient profile, pathology, and language. Returns structured exercises with instructions, target phonemes, difficulty level, and therapist tips.
Inputs: message (required), ageLevel (required), speechChallenge (required), language.
vocametrix_generate_therapy_planA
Launch an asynchronous LangGraph-powered therapy plan generation from session audio embeddings. Returns a therapy_session_id. Use vocametrix_get_therapy_status to poll progress, then vocametrix_get_therapy_result to retrieve the plan once complete (~30–120 seconds). Requires wav2vec embeddings — run eGeMAPS or embedding extraction first.
Inputs: sessionMetadata (required), wav2vecOutput (required), patientAnamnesis.
vocametrix_generate_word_listA
Generate a word list targeting a specific phoneme with pronunciation hints and difficulty progression. Useful for articulation therapy, phonological awareness drills, and accent training.
Inputs: language (required), patientAge (required), targetSound (required).
vocametrix_get_therapy_resultA
Retrieve the completed therapy plan result. Only call when vocametrix_get_therapy_status returns result_available = true or status = 'complete'. Returns the full therapy session with exercise plans, clinical narrative, and HTML report path.
Inputs: sessionId (required).
vocametrix_get_therapy_statusA
Poll the status of an async therapy plan generation or stuttering classification session. Statuses: pending → processing → pending_approval → complete (or failed). result_available = true means you can call vocametrix_get_therapy_result.
Inputs: sessionId (required).
vocametrix_interpret_spelling_attemptA
Interpret a speech-to-text transcription of a spelling attempt and give intelligent feedback. Returns whether the spelling matches, an explanation of differences, and correction guidance. Useful for spelling therapy apps where children spell words aloud.
Inputs: transcription (required), targetWord (required), language.
vocametrix_interpret_voice_metricsA
Translate raw voice metrics (jitter, shimmer, HNR, CPPS, F0, etc.) into clinical-language interpretation with severity classification (normal / mild / moderate / severe) and actionable recommendations. Useful when you have metric values from other tools and want a clinician-readable summary.
Inputs: metrics (required), patientAge (required), patientGender, languageCode.
vocametrix_measure_sound_levelA
Measure sound level in dB SPL over a specified time window in an audio file. Useful for environmental noise assessment, vocal loudness measurement, and calibration tasks. Note: startSec must be > 0 (use 0.001 for the start of the file).
Inputs: audioPath (required), startSec, endSec.
vocametrix_synthesize_speechB
Synthesize speech from text using Azure neural text-to-speech. Returns an audio URL and word-level timing data. Supports all Azure Neural voice names for the requested locale.
Inputs: text (required), speakerLocale, voiceName.
vocametrix_synthesize_speech_with_timingA
Synthesize speech via ElevenLabs v2 with per-character timing alignment. Returns audio data and a character-level timing map — useful for lip-sync, subtitles, and karaoke. Supports plain text or SSML markup.
Inputs: text (required), isSSML.
vocametrix_transcribe_audioA
Transcribe an audio file using Azure Speech-to-Text with streaming progress. Returns a transcriptionId and streams progress events via SSE until completion. Returns the final transcript and word-level timing. For long recordings, poll the progress events — transcription may take 30–120 seconds.
Inputs: audioPath (required), speakerLocale.
vocametrix_vocabulary_tutorA
Conversational vocabulary tutor adapting to learner profile (native language, target language, age, topic). Uses spaced repetition principles. Maintain conversation context via threadId.
Inputs: message (required), nativeLanguage (required), targetLanguage (required), ageGroup (required), +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 39 tools
Each tool targets a distinct function or metric, from acoustic analysis to therapy planning. Even similar tools like assess_pronunciation and assess_pronunciation_with_pitch are clearly differentiated by the additional pitch feature. No overlapping purposes.
All tools follow the 'vocametrix_verb_noun' snake_case pattern. Verbs like calculate_, assess_, generate_, get_ are used consistently for similar operations. No mixing of conventions.
39 tools is high, reflecting a broad domain. While each tool is focused, some could be combined (e.g., multiple calculate_ tools under a single analyze_voice_quality). Still within acceptable range for a comprehensive server.
Covers the full speech therapy workflow: assessment, diagnosis, plan generation, exercises, transcription, synthesis, and tutoring. No obvious gaps for the stated domain.
Maintenance
Related MCP Connectors
Official MCP server for OmniDimension. Drive voice agents, dispatch calls, and run bulk campaigns.
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
Official MCP server for Lovable, the AI-powered full-stack app builder.
FalaAI API MCP server: transcribe audio, diagnose conversations, audit compliance (ISO 18295-1).
Related MCP Servers
- AlicenseBqualityDmaintenanceMCP server for Synthesizer V AI Vocal Studio, which allows LLMs to create/edit vocal tracks e.g. adding lyrics to the melody.616Apache 2.0
- AlicenseAqualityDmaintenanceOfficial ElevenLabs MCP server for text-to-speech, voice cloning, audio transcription, and sound generation.24MIT
- AlicenseNot gradedqualityDmaintenanceOfficial MCP server that enables interaction with ElevenLabs Text to Speech and audio processing APIs. It allows generating speech, cloning voices, transcribing audio, and creating sound effects through natural language.MIT

@speechweave/mcpofficial
AlicenseAqualityBmaintenanceMCP server for SpeechWeave transcription, enabling AI assistants to transcribe local files and URLs via wait-first or async tools.659 npm1MIT