What is Speech-to-Text (STT)?
TL;DR
AI technology that automatically converts speech to text. Essential for meeting transcription and subtitle generation.
Speech-to-Text (STT): Definition & Explanation
Speech-to-Text (STT, automatic speech recognition) is an AI technology that automatically converts human speech into text. Since OpenAI's Whisper model, recognition accuracy has improved dramatically, enabling high-precision multilingual speech recognition. Services like Otter.ai, Fireflies.ai, Notta, and tl;dv use this technology for automatic meeting transcription, video subtitle generation, call center analysis, and medical dictation. It supports both real-time recognition and batch processing, with features like speaker diarization (identifying who said what) and timestamp annotations.