Try Sepia https://sepia-framework.github.io, it is an open source assistant, works very good. - Source: Hacker News / over 1 year ago

I haven't used it personally but https://sepia-framework.github.io/ appears to be similar to that. Source: over 1 year ago

Also, I learned about this replacement to apples siri. https://sepia-framework.github.io/ gonna check it out.. Source: almost 2 years ago

Feed the audio file to Google's text-to-speech engine: Https://cloud.google.com/speech-to-text. Source: 12 months ago

Also known as voice-to-text, speech recognition software is another technology that provides computer assistance and increased accessibility to disabled individuals. With it, blind and visually impaired people can use the Internet to navigate, type, as well as interact with web content using their voice. Source: about 1 year ago

Free 60 min - https://cloud.google.com/speech-to-text. Source: over 1 year ago

I was looking to do something similar, but a long time ago, so I don't know the latest. However Google's Speech To Text seems to be quite good: https://cloud.google.com/speech-to-text/ and I believe it can transcribe "live" if that is what you are after. Source: over 1 year ago

I use Vosk for speech recognition but also plan to add support for Google Speech-To-Text and Microsoft Azure Speech to text. Source: over 1 year ago