AI Transcription – Speech to Text · Using Whisper

Transcribe audio and video files in a blink, automatically, all offline, and with highly accurate results. AI Transcription uses OpenAI’s Whisper technology and Apple Speech Recognition to convert speech (like in podcasts, presentations, lectures, or voice messages) into text and subtitles.

Features

• AI-powered audio-to-text converter

• Just drag & drop: Transcription starts automatically

• Supercharged by OpenAI’s Whisper and Apple Speech Recognition

• Privacy by Design: Your audio never leaves your Mac. Everything is computed on-device, all offline.

• User-friendly, lightweight design, yet powerful

• Export transcriptions as plain text, CSV, SRT, and WEBVTT files

• Timing: Split segments by words, sentences, duration

• Supports input formats like MP3, WAV, CAF, AIFC, M4A, MP4

This app wouldn’t be possible without the work of Georgi Gerganov an his excellent port of OpenAI’s Whisper model in C/C++ (whisper.ccp)