AI Glossary · Definition
What is Speech-to-text?
Speech-to-text is AI that converts spoken audio into written text, also called transcription.
By DAIDU EditorialUpdated
Speech-to-text, explained
Speech-to-text powers meeting notes, call transcripts, voice notes and voice assistants. Combined with a language model, transcripts can be summarised into decisions and actions. Accuracy varies with audio quality, accents, background noise and languages, and mixed Arabic-English speech is a useful test. Recording and transcribing people requires their awareness and should follow your privacy rules. Test any tool with your own recordings before relying on it.
Example
A sales team transcribes recorded client calls and automatically adds a summary and next steps to the CRM.