Whisper

Whisper is an automatic speech recognition (ASR) system developed by OpenAI. It converts spoken audio into text (speech-to-text) and more.

https://github.com/openai/whisper

Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multitasking model that can perform multilingual speech recognition, speech translation, and language identification.

https://github.com/ggml-org/whisper.cpp

High-performance inference of OpenAI’s Whisper automatic speech recognition (ASR) model

https://whisper.ggerganov.com/
Running in browser.