Sense API enables developers to extract various non-verbal information from an audio input with the power of audio processing and neural network techniques. It is robust against noises and different types of recording environments, so it can be used for analyzing input audio from various IoT devices such as smart speakers or IP cameras, not to mention its potential usage in searching through video clips.

To date, Sense API is the only publicly available API online for machine listening, a rapidly emerging technology. It supports both prerecorded audio and real-time streaming as inputs, and multiple audio encodings are supported including mp3, wav, and FLAC.

If you need any help or support, please do not hesitate to contact us at support@cochlear.ai.