Transcribe & edit by speech Use auto-editor's whisper.cpp (Whisper or NVIDIA Parakeet models) or Apple Speech backend to transcribe audio. Cut a timeline based on subtitle content with / . Transcribe — Set to a model path. Three backends, chosen by the model: - Whisper : , , , … (https://huggingface.co/ggerganov/whisper.cpp). 99+ languages, , . - Parakeet : any model with "parakeet" in the filename, e.g. (https://huggingface.co/ggml-org/parakeet-GGUF). Faster than Whisper at comparable English accuracy; language is auto-detected. , , and are rejected. - Apple : the magic model name uses Apple…