{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/fbabb2da83c249d3a0a09b3adcc4a4e6\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/fbabb2da83c249d3a0a09b3adcc4a4e6-ab814d7527bfa513.gif","duration":173.493,"title":"Push-to-Talk: Personal Voice Transcription Powered by AI","description":"In this video, I introduce Push-to-Talk, a lightweight desktop app that transcribes your voice directly into any open window, eliminating the need for copy and paste. There are two modes: Push-to-Talk mode for instant transcription and toggle mode for longer reflections. I also discuss future plans, including offline models for privacy, custom glossaries, and cross-platform support. To get started, simply visit the release page on GitHub, download the zip files, and set up your OpenAI keys. I encourage you to try it out as it's completely free and only takes a few minutes to set up.\n\nDownload: https://github.com/yixin0829/push-to-talk/releases/tag/v0.2.0"}