# Vocametrix

> Voice analysis, speech therapy, and acoustic measurement platform with 20+ API endpoint groups (AVQI, DSI, CPP, HNR, jitter/shimmer, formants, prosody similarity, pronunciation assessment, speech-to-text, text-to-speech, eGeMAPS, and more). Used by speech-language pathologists, voice researchers, and developers building healthcare and education applications.

Base URL: `https://platform.vocametrix.com`. Auth: `X-API-Key` header (except SSE endpoint which uses `?apiKey=` query string).

## Documentation

- [API reference (Markdown)](https://www.vocametrix.com/api-docs.md): Full machine-readable API documentation — all endpoints, parameters, responses, and cURL examples.
- [API reference (plain text)](https://www.vocametrix.com/api-docs.txt): Same content as plain text for tools that prefer it.
- [OpenAPI 3.1 spec](https://www.vocametrix.com/openapi.json): Machine-validatable schema for all endpoints — compatible with Swagger UI, Redoc, and agent tool-calling.
- [Interactive API docs](https://www.vocametrix.com/api-docs): Human-readable rendered documentation.
- [Pricing & rate limits](https://www.vocametrix.com/pricing)
- [Registration / API key](https://www.vocametrix.com/registration)

## Upload patterns

Two upload patterns exist — choose by endpoint group:

1. **blob-url pattern** (Pronunciation, Speech-to-Text, Sound Level): `POST /api/get-blob-url` → `PUT <uploadURL>` → POST analysis with `blobURL`.
2. **assignFileId pattern** (all Praat calculators: AVQI, DSI, CPP, HNR, Spectral, Formants, S/Z, GNE, H1*-H2*, VRP, Jitter/Shimmer, ABI, Voice Dynamics, Prosody Similarity, eGeMAPS, Phoneme, Stuttering, Estonian Vowel): `POST /api/assignFileId` (multipart: `audio`) → use returned `fileId`.

## Async result patterns

- **SSE**: `POST /api/offline-speech-to-text` → subscribe `GET /api/transcription-progress/:id?apiKey=YOUR_KEY` (query-string auth only).
- **Polling**: `/api/classify-stuttering` and `/api/generate-therapy-plan` return a session/job id; poll `/api/therapy-status/:id` until complete, fetch result from `/api/therapy-result/:id`.
- All other endpoints are synchronous.

## APIs

### Core Speech Analysis

- Pronunciation Assessment API
- Speech to Text API
- Text to Speech API

### Voice Quality Metrics

- Acoustic Voice Quality Index (AVQI) Calculator API
- Dysphonia Severity Index (DSI) Calculator API
- Cepstral Peak Prominence (CPP) Calculator API
- Multi-band Harmonics-to-Noise Ratio (HNR) Calculator API

### Advanced Voice Analysis

- Advanced Spectral Measures Calculator API
- Formant Statistics Analysis (F1-F4) Calculator API
- S/Z Ratio Analysis Calculator API
- Glottal-to-Noise Excitation Ratio (GNE) Calculator API
- H1*-H2* Voice Source Analysis API
- Voice Range Profile (VRP) Analysis
- Jitter & Shimmer Perturbation Analysis API v.03 (Scientifically Validated)
- Extended Acoustic Calculators (ABI, Voice Dynamics, Prosody Similarity)

### Audio Measures

- Audio Measures (Sound Level, eGeMAPS)

### Phoneme & Classification

- Phoneme & Audio Classification (Phonemes-Live, Stuttering, Estonian Vowel)

### Therapy Planning

- Therapy Plan Generator API (Python workflow)

### AI Agents

- AI Agents

## Optional

- [Privacy & GDPR](https://www.vocametrix.com/privacy)
- [Terms of service](https://www.vocametrix.com/terms)