Speechmatics

About

 

Speech Recognition

Simply provide your audio or video content and receive a full transcript. We use an innovative deep learning approach to Speech recognition, and are committed to providing high accuracy and efficiency across multiple languages. Our speech recognition solutions can be operated from the cloud or within your own premises making it easy to integrate with other applications to provide complete solutions to your needs.

Features

  • Delivered from the Cloud or from your own premises deployment
  • Interact via Web console or restful API
  • Supports multiple languages
  • Recognises speaker changes and punctuation
  • Provides word confidence scores and timings