# vocametrix AI-powered voice analysis MCP server for speech-language pathologists and voice researchers. Provides 38 clinical-grade tools for acoustic analysis — jitter/shimmer, HNR, AVQI, formants, voice range… ## Quick Start ```bash # Connect this server (installs CLI if needed) npx -y smithery mcp add patrick-marmaroli/vocametrix # Browse available tools npx -y smithery tool list patrick-marmaroli/vocametrix # Get full schema for a tool npx -y smithery tool get patrick-marmaroli/vocametrix vocametrix_calculate_avqi # Call a tool npx -y smithery tool call patrick-marmaroli/vocametrix vocametrix_calculate_avqi '{}' ``` ## Direct MCP Connection Endpoint: `https://vocametrix.run.tools` **Required config:** - `vocametrixApiKey` (query) — Your Vocametrix API key. Get one at https://www.vocametrix.com/registration — free trial includes 5 minutes of analysis or 5 API credits. ## Tools (38) - `vocametrix_calculate_avqi` — Calculate the Acoustic Voice Quality Index (AVQI), a clinically validated dysphonia score. AVQI combines acoustic param… - `vocametrix_calculate_dsi` — Calculate the Dysphonia Severity Index (DSI). DSI > 1.6 = normal voice; DSI < –1.6 = severe dysphonia. Requires a susta… - `vocametrix_calculate_cpp` — Calculate Cepstral Peak Prominence (CPP) from a sustained vowel. Higher CPP = better voice quality. Typical normal CPP:… - `vocametrix_calculate_hnr` — Calculate multi-band Harmonics-to-Noise Ratio (HNR) across frequency bands (80–8000 Hz) with age- and gender-specific n… - `vocametrix_calculate_jitter_shimmer` — Calculate jitter (period perturbation, PPQ5) and shimmer (amplitude perturbation) from a sustained vowel. Normal jitter… - `vocametrix_calculate_voice_range_profile` — Calculate the Voice Range Profile (VRP / ambitus / glissando) from a glissando recording. Returns frequency range (lowe… - `vocametrix_calculate_prosody_similarity` — Compare prosodic patterns between a model (reference) recording and a learner recording. Returns similarity scores for … - `vocametrix_calculate_spectral` — Extract advanced spectral measures from a sustained vowel: center of gravity, skewness/kurtosis, H1-H2 (breathiness ind… - `vocametrix_calculate_formants` — Compute F1–F4 formant statistics (mean, SD, range, CV, IQR) from a sustained vowel with vowel-space stability and artic… - `vocametrix_calculate_sz_ratio` — Calculate the S/Z phonation ratio (duration of sustained /s/ vs /z/). Normal ratio ≈ 1.0. Ratio > 1.4 suggests vocal fo… - `vocametrix_calculate_gne` — Calculate the Glottal-to-Noise Excitation (GNE) ratio from a sustained vowel. GNE ranges 0–1; values < 0.5 suggest incr… - `vocametrix_calculate_h1_h2` — Calculate the formant-corrected H1*–H2* voice source measure from a sustained vowel. H1*–H2* is sensitive to breathines… - `vocametrix_calculate_abi` — Calculate the Acoustic Breathiness Index (ABI) combining connected speech and sustained vowel. ABI aggregates CPPS, jit… - `vocametrix_calculate_voice_dynamics` — Compute intensity dynamics, pitch-intensity correlation, and composite scores for voice control, projection, stability,… - `vocametrix_assess_pronunciation` — Score pronunciation accuracy at phoneme level against a reference text. Returns accuracy, fluency, completeness, and pr… - `vocametrix_assess_pronunciation_with_pitch` — Pronunciation assessment enriched with per-word F0 (pitch) contours. In addition to accuracy/fluency/prosody scores, re… - `vocametrix_transcribe_audio` — Transcribe an audio file using Azure Speech-to-Text with streaming progress. Returns a transcriptionId and streams prog… - `vocametrix_synthesize_speech` — Synthesize speech from text using Azure neural text-to-speech. Returns filePath (saved WAV file) and dataUrl (data URI … - `vocametrix_measure_sound_level` — Measure sound level in dB SPL over a specified time window in an audio file. Useful for environmental noise assessment,… - `vocametrix_extract_egemaps` — Extract the full openSMILE eGeMAPSv02 feature set (88 acoustic features) from a sustained vowel. Features include F0, j… - `vocametrix_detect_phonemes` — Detect French phonemes in an audio recording using a deep-learning classifier. Returns phoneme labels with confidence s… - `vocametrix_classify_stuttering` — Classify stuttering disfluency patterns in a speech recording (async, ~30–120 seconds). Returns disfluency types (repet… - `vocametrix_interpret_voice_metrics` — Translate raw voice metrics (jitter, shimmer, HNR, CPPS, F0, etc.) into clinical-language interpretation with severity … - `vocametrix_generate_exercises` — Generate personalized speech therapy exercises tailored to patient profile, pathology, and language. Returns structured… - `vocametrix_generate_word_list` — Generate a word list targeting a specific phoneme with pronunciation hints and difficulty progression. Useful for artic… - `vocametrix_chat_speech_therapist` — Expert speech therapy assistant providing role-based guidance. Adapts its answers depending on whether the user is a th… - `vocametrix_convert_french_to_ipa` — Convert French words or phrases to International Phonetic Alphabet (IPA) transcription. Accepts a single string or an a… - `vocametrix_interpret_spelling_attempt` — Interpret a speech-to-text transcription of a spelling attempt and give intelligent feedback. Returns whether the spell… - `vocametrix_check_syntax` — Analyze text for grammar and syntax errors with severity classification (error/warning/info). Returns overall score, pe… - `vocametrix_vocabulary_tutor` — Conversational vocabulary tutor adapting to learner profile (native language, target language, age, topic). Uses spaced… - `vocametrix_adapt_exercise` — Adapt a speech therapy exercise to a specific learner profile (ADHD, dyslexia, dysgraphia, dyspraxia, Tourette, autism)… - `vocametrix_generate_therapy_plan` — Launch an asynchronous LangGraph-powered therapy plan generation from session audio embeddings. Returns a therapy_sessi… - `vocametrix_get_therapy_status` — Poll the status of an async therapy plan generation or stuttering classification session. Statuses: pending → processin… - `vocametrix_get_therapy_result` — Retrieve the completed therapy plan result. Only call when vocametrix_get_therapy_status returns result_available = tru… - `vocametrix_approve_therapy_plan` — Human-in-the-loop approval gate for generated therapy plans. Actions: 'approve' (locks and delivers plan), 'reject' (di… - `vocametrix_full_voice_assessment` — Run a comprehensive clinical voice assessment in a single call. Executes AVQI, CPP, multi-band HNR, jitter/shimmer, and… - `vocametrix_batch_pronunciation` — Assess pronunciation for all WAV files in a folder against a common reference text. Returns a table (Markdown + JSON) w… - `vocametrix_full_therapy_workflow` — End-to-end therapy plan generation with automatic polling and human-in-the-loop approval. Generates a therapy plan from… ```bash # Get full input/output schema for a tool npx -y smithery tool get patrick-marmaroli/vocametrix ``` ## Resources - `vocametrix://docs/api` — Vocametrix API quick reference: auth, rate limits, audio requirements, error codes - `vocametrix://recording-guide` — Recording protocols for all Vocametrix voice analysis tools: sustained vowel, connected speech (with language-specific … - `vocametrix://thresholds/avqi` — Clinical reference thresholds for AVQI - `vocametrix://thresholds/dsi` — Clinical reference thresholds for DSI - `vocametrix://thresholds/cpp` — Clinical reference thresholds for CPP - `vocametrix://thresholds/hnr` — Clinical reference thresholds for HNR - `vocametrix://thresholds/jitter-shimmer` — Clinical reference thresholds for JITTER-SHIMMER - `vocametrix://thresholds/gne` — Clinical reference thresholds for GNE - `vocametrix://thresholds/avqi_locales` — Clinical reference thresholds for AVQI_LOCALES ## Prompts (3) --- *Response truncated. Use `npx -y smithery` for complete data.*