I would like to thank Whisper from OpenAI for making it easy to develop my application. Their tools simplified the use of AI models for audio, allowing for a more straightforward and efficient development process.
Whisper enables accurate speech-to-text conversion, allowing our avatars to process and understand spoken input, ensuring seamless communication and enhanced user interaction.
Whisper was open sourced by OpenAI and is able to run really well directly on Apple Hardware using the Apple Neural Engine. Podcasts are about to get some really cool features and I'm looking forward to helping build them!
