Technical specifications across our product offering
Batch ASR
Transcription of pre-recorded audio and video available in flexible deployment options.
Real-Time ASR
Transcription provided in parallel to input audio being streamed through the Speechmatics engine.
Looking for more technical detail? Our Support content may help.
Whitepapers and eBooks
Read about how we develop a single English language model, Global English, to support all English accents for use in speech-to-text.
Find out more about our machine learning framework for building languages.
Have you been wondering about what to do with all your data? In this short ebook, we explain how to make the most of a data surplus.
From the Blog
Past Webinars
