What is speech-to-text?
Speech-to-text, also called automatic speech recognition, is technology that converts spoken language into written text. It analyzes audio for sounds and patterns and maps them to words. It underpins dictation, live captions, voice search, and voice-controlled applications.
- Converts audio into words using acoustic and language patterns.
- Accuracy can vary with accent, background noise, and vocabulary.
- In Overscope it feeds map-building, not a transcript document.
How Overscope relates
Overscope uses speech-to-text as an intermediate step only: it interprets what you say to build a mind map, and does not surface the recognized text as a transcript.