Unlocking the power of voice to assess wellness.

Our real-time speech analysis API detects diseases and clinical conditions earlier and less invasively than traditional methods.

Voice in. Data out.

Our state-of-the-art speech analysis API seamlessly extracts vocal features and returns results in real-time using as little as 20 seconds of conversational speech.

Canary's patented technology analyzes acoustic and linguistic features to model and screen for disease. Built on a robust cloud architecture and utilizing the latest in language processing and machine learning modeling, the Canary API delivers secure, cost-effective solutions.

Vocal feature extraction

Extract limitless vocal features to model and screen for mood disorders, respiratory conditions, and clinical deterioration.

Deliver assessments

Collect actionable survey data in seconds using our non-invasive platform. Our machine learning system aggregates data and models from your data pool.

Real-time analysis

Screen for responses to treatment and monitor patient outcomes using Canary's proprietary data modeling.

Predictive health

Monitor wellness over time using Canary's built-in reporting. Translate healthcare assessments into objective, quantifiable data.

Secure cloud infrastructure

Built on industry-leading cloud platforms, Canary is fully HIPAA-compliant and maintains stringent data security measures.

Seamless integration

Our API-first, cost-effective solution makes it easier than ever to seamlessly integrate speech analysis into your organization.

API Features

We've made it easier than ever to harness the power of speech analytics in your business.

HIPAA-compliant
Fully documented
Production and sandbox environments
RESTful API format, with JSON and XML responses available
OAuth 2.0 authentication
Predictable resource-oriented URLs

Form-encoded request bodies
JSON-encoded responses
Standard HTTP response codes, authentication, & verbs
Audio processing
Vocal scoring

Start using the Canary API today

Get Started