.pg-hero{text-align:center;padding:56px 20px 8px;max-width:900px;margin:0 auto} .pg-eyebrow{color:#3BF08A;font-weight:700;letter-spacing:.08em;font-size:13px;text-transform:uppercase;margin:0 0 14px} .pg-hero h1{font-size:clamp(30px,4.4vw,48px);line-height:1.15;margin:0 0 18px;color:#E8EDF2;font-weight:800} .pg-hero p.pg-sub{color:#8A95A5;font-size:16px;line-height:1.6;max-width:720px;margin:0 auto 26px} .pg-cta-row{display:flex;gap:12px;justify-content:center;flex-wrap:wrap;margin-bottom:10px} .pg-btn{display:inline-flex;align-items:center;justify-content:center;padding:13px 26px;border-radius:10px;font-weight:700;font-size:15px;text-decoration:none} .pg-hero a.pg-btn-primary,.pg-btn-primary{background:#3BF08A!important;color:#06140C!important} .pg-btn-primary:hover{filter:brightness(1.08)} .pg-hero a.pg-btn-ghost,.pg-btn-ghost{background:transparent!important;border:1px solid #232B37;color:#E8EDF2!important} .pg-btn-ghost:hover{border-color:#3BF08A;color:#3BF08A!important} .pg-note{color:#7A8594;font-size:12.5px;margin-top:6px} .pg-strip{display:grid;grid-template-columns:repeat(4,1fr);gap:20px;max-width:1000px;margin:34px auto 0;padding:0 20px;text-align:center} .pg-strip .i{font-size:26px} .pg-strip .t{color:#E8EDF2;font-weight:700;font-size:14px;margin:8px 0 6px} .pg-strip .d{color:#8A95A5;font-size:12.5px;line-height:1.45} .pg-divider{border:none;border-top:1px solid #1C232E;max-width:900px;margin:44px auto} .pg-sec{max-width:1060px;margin:0 auto;padding:0 20px;text-align:center} .pg-sec h2{font-size:clamp(24px,3vw,34px);color:#E8EDF2;margin:0 0 10px;font-weight:800} .pg-sec p.lead{color:#8A95A5;font-size:15px;margin:0 auto 28px;max-width:700px} .pg-grid{display:grid;grid-template-columns:repeat(3,1fr);gap:16px;text-align:left} .pg-card{background:#10141B;border:1px solid #1C232E;border-radius:14px;padding:20px;transition:transform .25s ease,border-color .25s ease;display:flex;flex-direction:column} .pg-card:hover{transform:translateY(-6px);border-color:#3BF08A} .pg-card .i{font-size:24px} .pg-card h3{color:#3BF08A;font-size:15px;margin:12px 0 8px;font-weight:700} .pg-card p{color:#8A95A5;font-size:13px;line-height:1.5;margin:0} .pg-shot-grid{display:grid;grid-template-columns:repeat(3,1fr);gap:16px;margin-top:24px} .pg-shot{position:relative;border:1px solid #1C232E;border-radius:10px;overflow:hidden;background:#10141B;cursor:zoom-in;aspect-ratio:4/3;display:flex;align-items:center;justify-content:center;transition:border-color .2s ease,transform .2s ease} .pg-shot:hover{border-color:#3BF08A;transform:translateY(-3px)} .pg-shot img{width:100%;height:100%;object-fit:contain;display:block} .pg-lb{display:none;position:fixed;inset:0;background:rgba(0,0,0,.92);z-index:99999;align-items:center;justify-content:center;flex-direction:column} .pg-lb.open{display:flex} .pg-lb img{max-width:92vw;max-height:80vh;object-fit:contain;border-radius:8px} .pg-lb-cap{color:#8A95A5;font-size:13px;margin-top:14px;text-align:center;padding:0 20px} .pg-lb-close{position:absolute;top:18px;right:26px;color:#E8EDF2;font-size:34px;cursor:pointer;line-height:1;background:none;border:none} .pg-lb-nav{position:absolute;top:50%;transform:translateY(-50%);color:#E8EDF2;font-size:44px;cursor:pointer;background:none;border:none;padding:10px 18px} .pg-lb-prev{left:10px}.pg-lb-next{right:10px} .pg-lb-count{color:#7A8594;font-size:12px;margin-top:6px} .pg-hist{background:#10141B;border:1px solid #1C232E;border-radius:14px;padding:22px;max-width:900px;margin:0 auto;text-align:center} .pg-hist h2{margin:0 0 12px} .pg-hist li{color:#8A95A5;font-size:14px;list-style:none} @media (max-width:900px){.pg-strip{grid-template-columns:repeat(2,1fr)}.pg-grid{grid-template-columns:repeat(2,1fr)}.pg-shot-grid{grid-template-columns:repeat(2,1fr)}} @media (max-width:560px){.pg-grid{grid-template-columns:1fr}.pg-shot-grid{grid-template-columns:1fr}}

100% Free · Version 1.1.2

TranscribeGeek: turn recordings into text on your own machine

Drop in audio or video and get a transcript out, plus a subtitle file if you want one. OpenAI’s Whisper models run locally on your own processor. No account, no server, no upload, and no cap on how much you transcribe.

Windows 10 or 11, 64-bit · self-contained installer · nothing else to install


🆓
100% free
No Pro tier, no ads, no per-minute cap
🔒
Runs on your machine
The recording is never uploaded, ever
📝
Text and subtitles
A plain .txt and a SubRip .srt, side by side
🌍
22 languages
Or let it work out the language itself

Video Demo

Twenty seconds: the queue, the models and the Settings screen that states what TranscribeGeek will not do. No sound – it is a walkthrough, not a sales pitch.

Everything you need to get words out of a recording

TranscribeGeek is a proper Windows application built around whisper.cpp. The queue, the models and the output are all handled for you, and nothing ever leaves the machine.

🎙️

Audio and video, either way

WAV, MP3, M4A, FLAC, OGG, Opus, WMA, AAC, MP4, MKV, MOV, AVI and WebM. Video files have the audio pulled out for you automatically.

📄

Transcript and subtitles

A plain text transcript beside the source file, with or without timestamps, and a SubRip .srt subtitle file alongside it if you tick the box.

📚

A real queue

Drop in twenty files and walk away. They are worked through one at a time on purpose. Whisper already uses every core, so two at once makes both slower.

🌍

22 languages, or automatic

Pick the language if you know it, or let Whisper detect it. Telling it is always more accurate than letting it guess.

🧠

Four model sizes

Tiny for a quick check, Small for everyday work, Medium when the recording is difficult. Downloaded on request and kept. Nothing is bundled into the installer.

🛡️

It never overwrites

If a transcript of that name is already there, the next one is numbered. Your earlier work is never silently replaced.

🔌

ffmpeg, if you have it

MP3 and MP4 need ffmpeg to decode. TranscribeGeek runs it as a separate program if it finds one and says so plainly if it does not. It never quietly downloads a 90 MB binary you did not ask for.

🔄

Update checker

Checks only when you click Check for updates, and never installs anything silently.


See it in action

Three screens: the queue, the models, and a Settings page that states plainly what TranscribeGeek will not do.

The Transcribe screen. The queue, the model and the output options in one place
The Models screen. Sizes shown honestly before anything is downloaded
The Settings screen. What TranscribeGeek will not do, in plain words
(function(){ // Built from the thumbnails on this page rather than written out again below them. // The list used to be a second hardcoded copy, so any page that borrowed this block // inherited the screenshots it was copied from. Derived, that cannot happen again. var shots = Array.prototype.map.call(document.querySelectorAll('.pg-shot'), function(el){ var im = el.querySelector('img'); return { src: (im && (im.getAttribute('data-full') || im.getAttribute('src'))) || '', cap: (im && im.getAttribute('alt')) || '' }; }).filter(function(s){ return s.src; }); var lb=document.getElementById('pgLb'), img=document.getElementById('pgLbImg'), cap=document.getElementById('pgLbCap'), cnt=document.getElementById('pgLbCount'), cur=0; function show(i){cur=(i+shots.length)%shots.length;img.src=shots[cur].src;img.alt=shots[cur].cap; cap.textContent=shots[cur].cap;cnt.textContent=(cur+1)+' of '+shots.length;} function open(i){show(i);lb.classList.add('open');document.body.style.overflow='hidden';} function close(){lb.classList.remove('open');document.body.style.overflow='';} document.querySelectorAll('.pg-shot').forEach(function(el){ el.addEventListener('click',function(){open(parseInt(el.dataset.i,10));});}); lb.querySelector('.pg-lb-close').addEventListener('click',close); lb.querySelector('.pg-lb-prev').addEventListener('click',function(e){e.stopPropagation();show(cur-1);}); lb.querySelector('.pg-lb-next').addEventListener('click',function(e){e.stopPropagation();show(cur+1);}); lb.addEventListener('click',function(e){if(e.target===lb)close();}); document.addEventListener('keydown',function(e){if(!lb.classList.contains('open'))return; if(e.key==='Escape')close();if(e.key==='ArrowLeft')show(cur-1);if(e.key==='ArrowRight')show(cur+1);}); })();

Who it’s for

Built by an IT pro who needed it, not a commercial suite trying to upsell you.

🎧

Anyone with a pile of recordings

Interviews, lectures, meetings, voice notes. Drop them in, walk away, come back to a folder of text files.

🎬

Video makers

A .srt file per video, ready to upload. No per-minute charge, no watermark, no monthly allowance to run out.

🏢

Anyone who cannot upload

Legal, medical, HR, anything under NDA. The recording never leaves the machine, so there is nothing to clear with anybody first.

Requirements

🖥️

Operating system

Windows 10 version 1809 or later, 64-bit. Windows 11 fully supported.

🔒

Rights

Runs as a normal user. No administrator rights are needed or requested.

📥

Download

About 37 MB for the installer. Speech models are downloaded separately, from inside the app, only when you ask for one.

⚙️

Prerequisites

None. .NET 8 is inside the build. ffmpeg is optional and only needed for formats other than plain 16 kHz mono WAV.

🏷️

Version

1.1.2. Released 1 September 2026.

📜

Licence

GPL-3.0. Free to use, including at work. No paid tier, ever.

Frequently Asked Questions

Is it really free? No Pro version, no catch?

Yes. TranscribeGeek is free to download and use, with no Pro tier, no ads, no per-minute cap and no bundled offers in the installer.

Does my recording get uploaded anywhere?

No. Transcription runs in the application, on your own processor. There is no account and no server. The only thing the app ever downloads is a speech model, from the Models screen, when you ask for one.

Why is there no speech model in the installer?

Because a model is between 78 MB and 1.5 GB and most people only ever use one of them. Bundling them all would make the download several times bigger for no benefit, so you pick one on the Models screen and it is fetched once and kept.

Do I need ffmpeg?

Only for formats other than plain 16 kHz mono WAV, so in practice, yes, for MP3 and MP4. Put ffmpeg.exe next to TranscribeGeek or anywhere on your PATH. It is deliberately not bundled: the common builds are GPL, and the app should not quietly download a 90 MB binary you did not ask for.

How long does a recording take to transcribe?

On a normal desktop processor, roughly real time with the Small model. An hour of audio takes about an hour. Tiny is several times faster and less accurate; Medium is several times slower and better on accents and poor recordings.

Will it overwrite my existing transcripts?

Never. Output is written beside the source file, and if a file of that name already exists the next one is numbered. The recording itself is only ever read.


Version History


Download TranscribeGeek today

Free, offline, and there is no limit on how much you transcribe.

Not code-signed, so Windows may warn on first run. Click More info, then Run anyway. SHA256 checksums

Windows may show a “Windows protected your PC” warning the first time you install it. That means SmartScreen has not seen the file before, not that anything is wrong with it. Here is why our builds are unsigned, and how to verify your download against its SHA-256 hash. We will never ask you to switch SmartScreen off.


Support

Found a bug, or want something added? Open an issue on GitHub and it will be read. Speaker labels. Who said what. Are the next thing planned.

.tgh-support-embed{margin:24px auto 0;font-family:-apple-system,BlinkMacSystemFont,"Segoe UI",Roboto,Helvetica,Arial,sans-serif;display:grid;grid-template-columns:repeat(auto-fit,minmax(280px,1fr));gap:16px;max-width:900px;padding:0 20px;text-align:left} .tgh-support-embed .tgh-card{background:#10141B;border:1px solid #1C232E;border-radius:14px;padding:18px;display:flex;flex-direction:column;gap:10px} .tgh-support-embed .tgh-card-top{display:flex;align-items:center;gap:12px} .tgh-support-embed .tgh-icon{width:42px;height:42px;border-radius:10px;display:flex;align-items:center;justify-content:center;font-size:20px;flex-shrink:0} .tgh-support-embed .tgh-title{font-size:14.5px;font-weight:600;color:#E8EDF2;line-height:1.3;margin:0} .tgh-support-embed .tgh-desc{font-size:12.5px;color:#8A95A5;line-height:1.45;margin:0;flex:1} .tgh-support-embed .tgh-btn{margin-top:4px;display:flex;align-items:center;justify-content:center;gap:6px;padding:10px 14px;border-radius:10px;font-weight:700;font-size:13px;text-decoration:none} .tgh-support-embed .tgh-btn-ghost{background:transparent!important;border:1px solid #1C232E;color:#E8EDF2!important} .tgh-support-embed .tgh-btn-ghost:hover{border-color:#3BF08A;color:#3BF08A!important} .tgh-support-embed .tgh-btn-kofi{background:#FF5E5B!important;color:#fff!important} .tgh-support-embed .tgh-btn-kofi:hover{filter:brightness(1.08)}
🐛

Found a bug, or want a feature?

Every report gets read, and feature requests genuinely shape what gets built next. Speaker labels. Who said what. Are the next thing planned.

Open an issue on GitHub
☕

Buy us a coffee

No tiers, no licence fees, no commercial restriction. If it saved you a subscription, a coffee is welcome. Never expected.

Support us on Ko-fi
.tgh-featured{max-width:900px;margin:38px auto 64px;padding:0 20px;text-align:center;font-family:-apple-system,BlinkMacSystemFont,"Segoe UI",Roboto,Helvetica,Arial,sans-serif} .tgh-featured-label{font-size:11px;font-weight:700;letter-spacing:1.4px;text-transform:uppercase;color:#7A8594;margin:0 0 14px} .tgh-featured-row{display:flex;flex-wrap:wrap;justify-content:center;gap:10px} .tgh-featured-item{display:inline-flex;align-items:center;gap:8px;background:#10141B;border:1px solid #1C232E;border-radius:10px;padding:10px 16px;font-size:13.5px;font-weight:600;color:#E8EDF2!important;text-decoration:none!important;transition:border-color .15s,color .15s} .tgh-featured-item:hover{border-color:#3BF08A;color:#3BF08A!important} .tgh-featured-dot{width:7px;height:7px;border-radius:50%;flex-shrink:0}