How to transcribe audio or video to text offline (and let Claude summarize it)
Turn voice memos, meetings, lectures and interviews into text with timestamps — privately on your computer, in 90+ languages, then let your AI summarize it.
Free · no account · 3 free uses of every tool · also for Mac (Intel), Windows, Linux
Online transcription services charge per minute and need your recording uploaded. Whisper, the open speech-recognition model, runs well on an ordinary laptop — GUI Hub packages it so you don’t need Python or a terminal.
Transcribe a file
- Download GUI Hub Essentials and open Transcribe Audio & Video.
- Pick the recording (MP3, M4A voice memo, WAV, MP4, MOV…).
- Choose the language (or leave it on automatic), keep Add timestamps on, and optionally choose where to save the .txt.
- Press Transcribe. The first run downloads the speech model once (about 200 MB); after that it works offline.
Translate while transcribing
Tick Translate to English to get an English transcript of a recording in another language.
Let your AI do the rest
With GUI Hub connected to Claude or Cursor: “Transcribe meeting.m4a and list the decisions and action items.” The assistant gets the full transcript back and can summarize, translate or turn it into notes — the audio never leaves your computer.
What powers it
OpenAI’s Whisper model (MIT) running in sherpa-onnx (Apache-2.0), with FFmpeg for reading any audio or video format. All downloaded from their official releases and verified before use.
Try it now
Free download — use it 3 times free. $9 once unlocks everything. Prefer to ask your AI? GUI Hub also works as an MCP server for Claude, Cursor and others.