AI and speech recognition software - tools, resources - OpenAI, and more

Mozilla Common Voice releases the largest to-date public domain voice dataset, including 18 languages, almost 1,400 hours of data from 42,000 contr... (2019)

We’ve trained and are open-sourcing a neural net called Whisper that approaches human level robustness and accuracy on English speech recognition. ... (2022)

Today I'll show you how to build the ultimate text to speech workflow, which will allow you to take perfect notes with your voice using ChatGPT and... (2023)