#transcription

Use this when a user has an audio recording they want to turn into a captioned short video, spoken-word clip, or social media short. The core is word-level timestamps: transcribe into word-by-word text, the user deletes words to cut the matching audio, AI marks key words for highlighting, and then it renders a vertical video with a black background, key words in gold, and captions that appear in sync with the sound. Use case: Turn an audio recording into a short social media video with key-word highlighting and captions synced to the sound.