// about Whisper
Whisper is OpenAI's open-source automatic speech recognition system, trained on 680,000 hours of multilingual audio from the web. It transcribes and translates speech in 99 languages with near-human accuracy, even handling accents, background noise, and technical vocabulary robustly. Developers embed Whisper in everything from voice assistants to interview transcription tools, and it underpins many commercial transcription services.