---
title: "What is Speech-to-text (STT / ASR)? Definition and Meaning in India | Vyora"
description: "Speech-to-text, also called automatic speech recognition (ASR), converts spoken audio into written text so software can understand what a caller said."
canonical_url: "https://www.vyora.ai/glossary/speech-to-text"
---

GLOSSARY · Voice AI · Updated 27 October 2026

# What is Speech-to-text (STT / ASR)?

Speech-to-text, also called automatic speech recognition (ASR), converts spoken audio into written text so software can understand what a caller said.

It is the first step in a voice agent. Accuracy depends on language, accent, audio quality and background noise, and phone calls are harder than studio audio because of compression and noisy lines.

Indian callers add extra difficulty: regional accents, mixed languages in one sentence, and names or product terms the model has not seen. Quality in Hindi and Hinglish is a key thing to test before choosing a platform.

## Common questions

What is the difference between ASR and STT?

In everyday use they mean the same thing. ASR is the research term, STT the product term.

## Related terms

-   [Text-to-speech (TTS)](https://www.vyora.ai/glossary/text-to-speech)
-   [Code-switching](https://www.vyora.ai/glossary/code-switching)
-   [Hinglish](https://www.vyora.ai/glossary/hinglish)

Definitions are general information for businesses in India, not legal advice. [All glossary terms](https://www.vyora.ai/glossary) · [Try Vyora free](https://www.vyora.ai/get-started)

We use cookies to improve your experience. By continuing to use this site, you agree to our [Privacy Policy](https://www.vyora.ai/privacy-policy).