The Voice Recognition technology has two features:
Grammar base recognition is a technology used to create the most accurate and reliable voice commands. Closely related to Voice Dictation, it takes the solution further with specific intent comprehension thanks to its design relying on grammar creation.
Voice Dictation (Speech To Text) is based on deep learning language models, that are used to transform audio signals into transcribed text. The results are statistically determined regarding the most frequent sentence structures and word occurrence regarding the context identified.
You can check this page to create a project with the voice recognition technology.