AIkyutai-labs/moshi: Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec. - kyutai-labs/moshi
AudioPen | The easiest way to convert messy thoughts into clear text
AudioPen transcribes and summarizes unstructured voice notes into text that’s easy to read and ready to share.
If you like thinking out loud, you'll love Audio Pen. It's like having a personal assistant who records and summarizes your thoughts.
