Audio — Audio Scribe V3 Dev Edition

Short Description

Audio Scribe V3 is a local speech-to-text desktop app for transcribing audio and video files into transcript formats like TXT, SRT, VTT, and JSON. It supports drag-and-drop, folders, batch transcription, queue management, output folder control, and a transcript preview panel.

DevKit Details

This Dev Edition includes the Python app file, Windows launcher, debug launcher, and README. It is intended for users who already use Python or are comfortable installing speech-to-text backends.

Requirements

Requires Python 3 and at least one speech-to-text backend installed. Recommended backend: faster-whisper. Fallback backend: openai-whisper. If using openai-whisper, FFmpeg may also be required on system PATH.

Included Files

AudioScribe_V3.pyw Launch_AudioScribe_V3.vbs Debug_AudioScribe_V3.bat README_AudioScribe_V3.txt

Best For

Creators, editors, podcasters, and video makers who need local transcript generation for audio or video files without relying on a cloud-only workflow.