Transcription App for Windows
Transcription App is a desktop application for Windows that turns audio and video recordings into accurate, editable transcripts without sending a single file to the cloud. It runs OpenAI’s Whisper models and NVIDIA’s Parakeet model directly on your PC, works out who is speaking, and gives you a complete workspace to correct, subtitle and export your transcripts.
It is built to run on the machine you already have, on 64-bit Windows, and on x64 and ARM devices alike. The app starts on the main processor and can use your graphics card where that is supported, and five models let you match the workload to the hardware rather than the other way round. Your recordings stay in a folder you choose, and the app only goes online to check your licence and download a model the first time you use it.
Transcription App is free forever with Whisper Base. Transcription App is freemium: download it, transcribe complete recordings of any length in as many projects as you like, and pay nothing. A subscription unlocks the more advanced models when you need extra accuracy or speed.
Download on MacOS
Download on Windows
Download on Linux
Works on the PC you already have
You do not need a workstation, and you do not need an x64 desktop either: ARM laptops are supported alongside x64 machines. Whisper Small and Whisper Base are there for laptops with less memory, and if a setting will not load on your machine the app falls back automatically and keeps the queue moving.
Use the graphics card when you have one
On Windows the app starts on the main processor and can use the graphics card where it is supported. Advanced users can pick the compute device, the number of processor cores and the model precision; everyone else can leave those on automatic.
Nothing leaves your PC
Transcription, speaker detection and speaker recognition all run on your device. Recordings and transcripts are stored in a local folder, nothing is uploaded for transcription, and your content is never used for training or analytics.
Choosing a model for your machine
Five models are included, and every one of them runs on your computer. The right choice depends on how much memory your PC has and whether you want the transcript quickly or as accurately as possible.
| Model | What it gives you | Best on |
|---|---|---|
| Whisper Large Turbo | Accuracy close to Whisper Large v3, with much faster processing | The recommended default, and the first one to try |
| Parakeet TDT 0.6B v3 | NVIDIA’s fast speech model, well suited to long recordings | Long files; set the language rather than leaving detection to the app |
| Whisper Medium | Generally more accurate than Small and Base, at some cost in speed | Desktops and laptops with memory to spare |
| Whisper Small | A balanced option | Laptops with less memory |
| Whisper Base | The fastest Whisper model | Quick drafts and older machines |
Each model is downloaded the first time you select it and then stays on your disk, so after the first run you are not waiting on anything but your own processor.
What you need to run it
| Windows version | Windows 11, fully tested. Windows 10 is expected to work but has not been tested as thoroughly |
| Architecture | x64 and ARM devices are both supported. Transcription runs on the main processor by default |
| Graphics card | Optional |
| Memory | 8 GB of RAM or more for Parakeet. Whisper models can need more, depending on the model and the settings you choose |
| Disk space | 500mb + 80mb to 2Gb depending on AI model |
| Download | .exe installer, no admin right needed |
| Internet | Only to check your licence and download a model the first time you use it |
Video files are transcribed from their audio track, and very large recordings are converted automatically by a media engine bundled with the app, so there is nothing else to install. Hours-long interviews, full episodes and multi-camera rushes are all fair game.
How much memory you need
Memory matters more here than raw processor speed, because a model has to be loaded into it before a single word is transcribed. As a rule of thumb, 8 GB of RAM is enough for Parakeet, the least memory-hungry of the models here and the quickest on long recordings. The Whisper models can ask for more, and how much depends on the settings you choose: a larger model, a higher precision and word-level timestamps all add to the bill.
On a laptop with 8 GB shared with everything else you have open, start with Whisper Large Turbo and drop to Whisper Small or Whisper Base if it struggles. Nothing breaks if you overreach. When a combination cannot load, the app falls back to one that works and keeps your queue moving instead of stopping with an error, and you can also lower the model precision or reduce the number of processor cores, each of which trades a little speed or accuracy for a smaller memory footprint.
From recording to finished transcript in five steps
Transcription App is organised around projects, so a single interview series, research study or production keeps its recordings, transcripts and notes in one place. Getting from raw audio to a clean transcript takes a few clicks.
- Create a project for a client, a study or a production.
- Add your audio or video files. Set the language, and switch on word-level timestamps and speaker segmentation if you need them.
- Queue as many files as you like. The app transcribes them one after another while you keep working on something else.
- Pick a model. Whisper Large Turbo is the recommended default, and lighter models are there for more modest machines.
- Review, correct and export. Your edits are saved automatically as you type.
You can try the editor before installing anything: the interactive demo on our home page is a live replica of the real screen, showing four models on the same recording with nothing corrected.
What the first run looks like
The first time you choose a model, the app downloads it. That is the one part of the process that needs a connection, and the one part you only do once. After that the model sits on your disk and the same transcription runs with the network off entirely, which matters if you work on a train, in a client’s office, or on a machine your organisation keeps off the internet.
You do not have to pay to find out, or ever. Transcription App is freemium: the free mode is free forever and transcribes complete recordings of any length with Whisper Base, in as many projects as you like. A real interview tells you more than any accuracy figure on a marketing page, including ours.
A workspace, not just a transcriber
Know who said what
Pyannote speaker models, also running on your PC, split each recording into speaker turns. Label a few segments per voice, run Speaker Recognition, then rename “Speaker 1” once and every matching segment follows, in a colour that stays the same across the project.
Search a whole project
Search every transcript in a project at once by keyword, narrow the results by speaker, and jump to the exact segment. Need tags for coding or advanced search with AND and OR? They are part of our sister research suite, Qualitativist.
Notes, subtitles and exports
Keep project notes open beside the transcript, style subtitles directly over your video, and export as a Word document, plain text, SRT or VTT subtitles, or structured JSON. Existing transcripts and subtitles can be imported in SRT, VTT, TXT, DOC, HTML or JSON.
Easy to justify to IT and to a client
Transcription App is a standalone application rather than a service your organisation has to approve, review and monitor. That removes most of the questions a security review would otherwise ask.
- No user accounts tied to your data
- No browser dashboards or cloud interfaces
- No uploads to third-party servers for processing
- No reuse of your content for training or analytics
Projects are saved as ordinary files in a folder you choose, which can be a managed drive or an encrypted disk, so they are backed up by whatever your organisation already uses. Your licence is linked to the devices you verify, and you can unlink a device from the settings whenever you change machines.
Built around four kinds of work
The same Windows app serves very different jobs, and each one has its own page with the details that matter for it.
- Qualitative researchers: private transcription of interviews and focus groups, with participant data never leaving the machine. For coding, advanced search and citations, see Qualitativist.
- Journalists: fast turnarounds on interviews and press conferences, with no copy of a source’s voice on someone else’s server.
- Film and TV professionals: a subtitle editor that previews and styles cues directly on the picture, exporting to SRT and WebVTT.
- Legal professionals: depositions and hearings transcribed in-house, with privileged audio kept off third-party servers.
Why run it on your PC rather than in a browser
Cloud transcription made sense when an ordinary PC could not run these models. That stopped being true, and once the speed argument goes, what is left is a service that holds your recordings, charges by the minute and has to be approved by whoever looks after data where you work.
| A cloud transcription service | Transcription App on your PC | |
|---|---|---|
| Where the recording goes | Uploaded to the provider’s servers, sometimes in another country | Stays on your PC, in a folder you choose |
| Who can reach it | The provider’s staff and subcontractors | You, and anyone you hand a project archive to |
| What IT has to approve | A new processor, its terms, its retention policy and its breach history | A desktop application, with no account and no data leaving the machine |
| Cost | Usually charged per audio minute | Flat subscription, unlimited use |
| Long recordings | Often capped or charged extra | No cap on the length of a file |
| Working offline | Not possible | Everything except the first download of each model |
| Corrections | Re-upload, or ask for a revision | Edited in place, with the audio one click away |
The one thing a cloud service still has is somebody else’s hardware. If your PC is old enough that even Whisper Base is a struggle, that is worth knowing before you subscribe to anything, which is exactly what the free mode is for.
Pricing
Start for free: Transcription App is freemium. The free mode is free forever, with no time limit and no cap on recording length, and runs on Whisper Base, so you can transcribe real work on your own PC without paying anything. Monthly and yearly subscriptions unlock the more advanced models.
Monthly
$2.29
Yearly
$22.99
Prices are also available in your local currency!
Please contact sam@transcription-app.com for discounts on multiple licenses or if you’re representing an organization.
Free forever, with Whisper Base:
- Free forever, not a trial: transcribe complete recordings of any length with Whisper Base.
- Unlimited projects, the transcription queue, speaker segmentation and recognition.
- The full transcript and subtitle editors, notes and keyword search.
- Exports to .txt, .srt and .json, transcript imports and full-storage backups.
- Your work stays yours: everything remains accessible if a subscription ends.
A subscription adds:
- The advanced AI models: Whisper Large Turbo, NVIDIA’s Parakeet v3, Whisper Medium and Whisper Small.
- Word (.doc) exports of transcripts and notes.
- WebVTT (.vtt) subtitle exports that keep your per-subtitle styling.
- Subprojects to organise larger work.
- Project archives to back up a project or send it to a colleague.
Need tags for coding, advanced search, a literature library or citations? They are part of our sister research suite, Qualitativist.
Questions about the Windows version
Do I need a graphics card?
No. On Windows the app starts on the main processor and works there, and it can use a graphics card where that is supported. If a combination does not work on your machine, it falls back automatically rather than stopping your queue. A lighter model such as Whisper Small or Base is the answer when a laptop is struggling.
Which versions of Windows are supported?
Windows 11 is fully tested, on both x64 and ARM devices, so a recent ARM laptop runs the app as well as a conventional x64 desktop. Windows 10 should also work, but we have not put it through the same testing yet, so treat it as likely rather than guaranteed and try the free mode before you commit.
How do I install it, and do I need administrator rights?
Transcription App for Windows comes as an .exe installer, and you do not need administrator rights to install it. The first time you pick a model, the app downloads it, and from then on it runs offline.
Does my audio ever leave my PC?
No. Transcription, speaker detection and speaker recognition all run on your device. Your recordings and transcripts are stored in a local folder and are never uploaded anywhere.
Do I need an internet connection?
Only occasionally. The app connects to check your licence and to download a model the first time you use it. Once a model is on your PC, you can transcribe completely offline.
Can I store my projects on a network or encrypted drive?
Yes. You choose the storage folder, so projects can sit on an encrypted disk or a drive your organisation manages and backs up. Each project is an ordinary folder of files rather than a database you need a tool to open.
Can I use one licence on my laptop and my desktop?
Your licence is linked to the devices you verify, and you can unlink a device from the settings whenever you change machines.
Which files can I transcribe?
Most common audio and video formats, including MKV. Video files are transcribed from their audio track, and very large files are converted automatically before transcription begins. You can also import existing transcripts and subtitles in SRT, VTT, TXT, DOC, HTML or JSON format.
Will it run on Windows 10?
It should. Windows 11 is the version we test fully, and Windows 10 is expected to work from a technical point of view but has not been through the same testing, so we would rather say that plainly than claim more than we have checked. If you are on Windows 10, try the free mode first and tell us if anything misbehaves.
Will it slow my PC down while it runs?
Transcription is demanding, so a long file will keep your processor or graphics card busy while it works. If you need the machine for something else at the same time, pick a lighter model such as Whisper Small or Base, or reduce the number of processor cores in the settings, and let the queue take a little longer.
What happens when I replace my PC?
Export each project as a single archive and import it on the new machine, which brings the recordings, transcripts and notes across together (project archives come with a subscription). Unlink the old PC in the settings and activate your subscription on the new one.
Your recordings, your PC, your transcripts
Download Transcription App, transcribe your first recording in minutes, and keep every word under your control.
Download on MacOS
Download on Windows
Download on Linux
Also available for Mac (Apple silicon and Intel, macOS 12 Monterey or later) and Linux (x86-64 and ARM). New to the app? Start with our tutorials.