Fuse Caption Studio

Fuse Caption Studio is a video and podcast captioning software for Apple chip Macs.

It supports on-device speech transcription, caption translation, timeline editing, and final export, eliminating the need to upload media or register an account. The software incorporates three recognition engines: NVIDIA Parakeet, OpenAI Whisper, and Apple Speech, automatically selecting the appropriate model based on the file and device. It covers approximately 100 languages, supports word-by-word time positioning, and has no import duration limit. Fuse Caption Studio A multi-layered timeline combined with audio waveforms, magnetic snapping, batch text and time editing facilitates the processing of multilingual content and speaker captions. Apple Intelligence assists with polishing, semantic search, and content summarization. Users can adjust fonts, strokes, backgrounds, positions, and animations such as karaoke and word-by-word pop-ups, and preview the effects at different screen ratios. Export supports various aspect ratios, up to 4K for burning captioned videos, and SRT, VTT, ASS, and iTT caption files. Pure audio can also be combined with dynamic waveforms to generate social media videos. The software requires macOS 26 or later; some advanced features require Pro.