Vocal Slice

Vocal Slice is a desktop application for people who regularly work through long voice recordings and need to quickly extract specific sections. The application combines local speech transcription with an interactive waveform. Users load an audio recording, Vocal Slice transcribes it locally with Whisper and generates word-level timestamps, and users can then highlight the exact words they want to keep. When text is selected, the waveform automatically moves to the corresponding audio region. Users can fine-tune the start and end boundaries and preview the selected section before exporting it. Vocal Slice supports WAV, MP3, FLAC, M4A, AAC, and OGG files of any length. WAV sources are cut byte-perfectly without re-encoding, preserving the original channel count, sample rate, and bit depth. Other supported formats are decoded to 24-bit WAV for export. The application includes filename templates so exported clips can automatically follow a user's preferred naming convention. This is particularly useful for production environments where dozens or hundreds of clips need to be delivered with consistent filenames. Users can also search for a particular word or phrase and find every occurrence in the recording. This makes the tool useful when comparing multiple takes of the same line or locating repeated phrases across a long recording. Vocal Slice supports multilingual Whisper models and currently provides access to all 99 languages supported by Whisper. English-only and multilingual models can be selected depending on the required balance between speed and language coverage. The application runs locally on Windows and macOS. Core transcription and audio slicing do not require an internet connection after the initial model download and license activation. Vocal Slice is sold as a one-time purchase rather than a subscription. The current license costs $29 and includes all features and future versions for up to three machines.