what3words introduces a new end-to-end speech recognition and post-processing Voice API powered by Speechmatics.
Speaking a street address into a voice interface can be time-consuming and frustrating. Thousands of duplicates exist and road names are easily confused, for example, Lawn Road and Lorne Road, which sound exactly the same when spoken. Numbers can make things even more confusing; saying ‘Take me to 241st Street’ can sound exactly the same as ‘Take me to 2, 41st Street’. In addition, addresses in different languages can be hard to pronounce for non-native speakers.
what3words is the first addressing system optimized for voice input, eliminating many of the frustrations of using voice to enter street addresses. Now what3words voice search can be built into apps, tools and services more easily with the what3words Voice API.
What is the what3words Voice API?
The what3words Voice API allows a user to say three words into any application or service, with it returning the what3words address and corresponding GPS coordinates, all through a single API call. For customers that want to enable a what3words-only voice search, this removes the commercial and technical complexities of fusing multiple APIs, meaning that developers can get it running in hours. The API is hosted by servers across several key international hubs, making the audio stream’s latency low enough to respond to the user in real-time.
The Speechmatics integration provides industry-leading speech recognition and machine learning capabilities that enable new what3words languages to be built on demand. This will unlock the potential of voice devices for more people across the globe.
Speechmatic’s machine learning would enable accurate speech recognition regardless of accent and can learn new languages.
The what3words Voice API currently supports Arabic, English, German, Hindi, Japanese, Korean, Mandarin and Spanish.
Author: Akhilesh Madasamy