# What is STT?

> Speech-to-Text

It is technology that listens to spoken words and converts them into written text.

## Overview
STT analyzes sound waves and translates them into words that the computer can understand. These systems produce text output by analyzing intonations and accents in human speech.

*Analogy: She is like the fastest secretary in the world, taking quick notes while you talk and never getting tired.*

## How it works
Voice data is received through the microphone, artificial intelligence analyzes this voice and writes the matching texts on the screen.

## Where it is used
It is used in meeting note-taking applications, voice command systems, and captioning tools.

## Commonly confused with
Mixed with voice synthesis (Text-to-Speech); One converts sound to text, the other converts text to sound.

## Frequently asked questions
**Can it understand different languages?**
Yes, modern STT models support many languages ​​and accents.

**Does it work in noisy environments?**
Advanced models can filter out background noise, but the margin of error may increase in very noisy environments.


## Related terms
- [Speech-to-Text](/en/dictionary/speech-to-text/)
- [Voice Cloning](/en/dictionary/voice-cloning/)
- [Whisper](/en/dictionary/whisper/)

## Related tools
- [Agents](/en/discover/agents/)
- [Speech to Speech](/en/discover/speech-to-speech/)
- [Transcribe.cpp](/en/discover/transcribe-cpp/)

---
Source: TreScout Dictionary · https://trescout.com/en/dictionary/stt/