Fast, local audio & video transcription & summarization
Turn audio and video into accurate text and smart summaries — fast, with faster-whisper and GPU acceleration. Runs fully offline, and the summary model can use online models.
large-v3-turbo-ct2 Stable GPU usage with low CPU and memory — your PC stays free for other work.
Free forever
May video2text be a helping hand on your learning journey.
Fast & flexible
Transcribe with a local model and keep everything offline, or plug in your own online model keys. Pick the setup that fits each job.
GPU Accelerated
Powered by faster-whisper with CUDA acceleration. Transcribe large files dramatically faster when a supported GPU is available.
Multi-language
Transcribe and summarize across many languages with automatic language detection — no manual switching required.
Smart Summary
Generate structured summaries with a local model, or connect your own online model. Turn hours of audio into key points.
Flexible Model Strategy
Use the built-in offline model, or plug in your own online transcription endpoint. Choose what fits each job.
Desktop & CLI
A friendly Windows GUI for everyday use and a CLI for scripting and batch jobs. One purchase works on multiple machines.
From file to summary in five steps
A simple, fast pipeline.
- 1
Pick a local file
Select an audio or video file from your computer.
- 2
Extract audio
The app extracts the audio track locally for transcription.
- 3
Transcribe
faster-whisper converts speech to text, with optional GPU acceleration.
- 4
Summarize
A local model (or your own online model) produces a structured summary.
- 5
Export
Save results as txt, json, srt, and more — ready to use.