Auto captions: generate subtitles from a video's own audio
How DijiFlow Dictate turns a video's soundtrack into timed subtitle lines on your computer, and which of its four out...
You have %itemCount% in your cart.Total being %total%
How DijiFlow Dictate turns your voice into text on your own computer, using local speech models and Apple Silicon. Explained in plain language.
Most dictation feels like magic until you ask the obvious question: where does my voice actually go? With DijiFlow Dictate, the honest answer is nowhere. You speak, text appears at your cursor, and not one word travels to a server. No account and no upload of your audio or text. That is not a privacy promise bolted on at the end — it falls out of how the app is built.
Three well-understood pieces make it work: the speech model that does the listening; the runtime that runs it efficiently on a Mac; and Apple Silicon, the chip that makes it feel instant. No prior knowledge needed — here is each one in plain terms.
At the heart of DijiFlow Dictate are speech recognition models that run on your own computer. A speech model is, in plain terms, a very large pattern-matcher trained on enormous amounts of audio paired with its transcript. From that data it learns how the sounds people make line up with the words they mean — across accents, background noise, and the natural pauses of real speech.
When you dictate, the model predicts the most likely sequence of words from your microphone audio, and it is genuinely good at it. On clear speech it reaches around 98% accuracy, and DijiFlow Dictate transcribes 29 languages with full support and recognises 90+ with auto-detect. Because it reads context rather than matching one word at a time, it copes with the messy way people actually talk.
This is the part that surprises people: the app and the intelligence are two different files. On a Mac, DijiFlow Dictate itself is small, about 34 MB. The speech models are the heavy part, ranging from roughly 300 MB to 6 GB depending on which you pick. On Pro and the trial, Large is the most accurate, Express is close to it and faster, and Fast is the quickest, in 16 languages including English; the free version uses Standard and Enhanced. You choose the balance of speed and accuracy that suits you.
You download a model once; after that, transcription needs no internet at all. That one-time step is exactly why your voice can stay on your machine.
A speech model is only useful if it runs quickly without draining your battery. That is the job of the runtime, the layer that runs machine-learning models on the device itself. Think of it as a translator and traffic controller: it takes a speech model and works out how to run it using the most suitable parts of your hardware.
On a Mac, DijiFlow Dictate's speech models are compiled for Apple's own machine-learning framework, which is part of macOS. That means the model is optimized specifically for Apple hardware instead of running as generic, slower code, so dictation keeps pace with natural speech while staying light on system resources. And it all happens locally: that framework is not a cloud service. It is part of the operating system that lets apps run machine-learning models privately on the device.
The last piece is the hardware. On modern Macs that means Apple Silicon — the M-series chips in machines running macOS 14 or later. These chips include a dedicated Neural Engine, a section of silicon built specifically to run machine-learning models fast and with very little power, with the GPU available through Metal when extra horsepower helps.
You configure none of this. The framework spreads the work across the right hardware automatically; you just speak, and the chip handles it in real time. That is the quiet advantage of on-device design: the same silicon that makes your Mac feel responsive is what makes private dictation practical.
Put the three pieces in order and the round trip is short — and entirely local.
Audio from your microphone is captured on the device, never streamed anywhere.
The model turns sound into words right there on Apple Silicon, in real time.
Your words appear in whatever app you are already in. Your words are not sent away, so there is nothing to leak.
Key takeaway
The model lives on your machine, so transcription is just local computation — there is no server in the loop to store, intercept, or quietly retain your voice.
Most voice tools are cloud services wearing an app icon: they need a connection and an account every time, because the model that understands you lives on someone else's hardware. DijiFlow Dictate flips that — you install once, and the work moves to your chip.
| How it behaves | DijiFlow (on-device) | Cloud dictation |
|---|---|---|
| Works after a one-time download | ✓ | ✗ |
| Transcribes with no internet | ✓ | ✗ |
| No account required | ✓ | ✗ |
| Audio stays on your device | ✓ | ✗ |
The same on-device approach extends to Windows 10 and 11, where DijiFlow Dictate runs on AMD, Intel, and NVIDIA GPUs. NVIDIA hardware needs CUDA and a current driver, but the principle is identical: your speech is transcribed locally, and your voice and text are not sent away.
There is nothing exotic happening here. DijiFlow Dictate is built on open, well-understood technology: speech models for the listening, Apple's machine-learning framework for the runtime, and Apple Silicon for the hardware. The decision that matters is keeping all of it on your device, so you get the convenience of modern dictation without ever handing your voice to anyone, across Free, Trial, and Pro.
If you would rather feel it than read about it, you can try private, on-device dictation free for 30 days on the Pro plan.