AI glossary
Speech-to-text (ASR)
What is a Speech-to-text?
Speech-to-text, also called automatic speech recognition (ASR), converts spoken audio into written text in real time. It is the 'ears' of an AI voice agent and affects how well the agent understands accents, languages and noisy lines.
Last reviewed · Dexorn Technologies
Low latency and accuracy on the caller's language are the main selection criteria for voice agents.
Transcripts produced by ASR also power call summaries and analytics.
Examples
- Live call transcription
- Voice notes to text
- Meeting transcripts
Put it to work
AI Voice Agents
Answer, qualify and book calls 24/7, in English and Hindi.