A Spark Between Voice and Text. OpenAudio has 17 repositories available. Follow their code on GitHub.

Fast speech-to-text for Mac and Windows. Responses in as little as 450ms. Create prompts, notes, messages, and docs with just your voice.

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 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.

Accurately convert speech to text with powerful AI models. Used by Fortune 500s, startups, and developers. Voted Best API of 2020, and funded by Insight Partners, Accel, and Y Combinator.

Otter is a smart note-taking app that empowers you to remember, search, and share your voice conversations. Otter creates smart voice notes that combine audio, transcription, speaker identification, inline photos, and key phrases. It helps business people, journalists, and students to be more focused, collaborative, and efficient in meetings, interviews, lectures, and wherever important conversations happen.