VoCut

VoCut is an AI-driven video and audio editing tool designed to make podcast editing as easy as editing a document. It supports speech recognition, transcription, automatic detection of verbal habits, removal of pauses, and includes features such as subtitle generation and export. It helps creators save more than 50% of their time by utilizing LLM and deep learning from the experience of many creators and editors, and artificial intelligence to enable one-click detection and deletion of silent clips, retakes, and filler words.

VoCut allows users to edit audio and video by editing the transcribed text. Simply upload your audio or video file, and VoCut will transcribe it. Then, delete the text corresponding to unwanted audio segments, and VoCut will automatically remove those segments from the audio/video.