Speech input


What is it?

Speech input (also known as speech-to-text or automatic speech recognition and dictation) allows users to interact with a digital device using voice commands, as well as to convert spoken words into text.

Voice-based user interfaces are used in many applications and industries including in-car systems, home automation, medical applications, call centres, aviation, language learning, and gaming. In recent years, they have become a popular way to interact with virtual assistants such as Apple’s Siri, Amazon’s Alexa and Echo, and Google Assistant.

Speech recognition has been used for quite some time to convert speech into text in telephone systems for Deaf and Hard-of-Hearing people. Voice-controlled interfaces are very useful for blind people and people with limited mobility. Speech input can also help people who have issues with reading and writing due to, for example, learning difficulties, cognitive disabilities, or brain injuries.

Speech input software is available as:

  • Part of most major operating systems.
  • Third-party dictation software.
  • Web services, websites, and browser plugins.