TranscribeKit v1.1.0 Multilingual

TranscribeKit is a Windows application that turns spoken audio and video into editable text without sending anything to the cloud. Drop in files like MP3, WAV, MP4, MKV, MOV or WEBM, then choose a Whisper model from Tiny up to Large depending on your hardware. Everything runs locally on your CPU, so no account, subscription or data collection is involved. Automatic language detection covers more than 60 languages, and voice activity detection skips silent stretches for tidier results. Inside the built-in editor you can correct words, check timecodes and search the whole transcript, then export to five formats. Optional AI translation into 19 languages runs through OpenRouter, and you can proofread with AI while approving every suggested change yourself. Subtitles can also be burned into MP4 video with adjustable font, size, color and position, including a dual-subtitle mode. It suits podcasters, researchers, filmmakers, journalists, educators and anyone working with spoken content on a Windows PC.