See It In Action

Your command center

The main screen puts everything within reach. Switch microphones, swap between the two transcription models (0.6B and 1.7B) for the right balance of speed and accuracy, change languages, and transcribe or translate files. Translate your voice output on the fly with simultaneous multi-language translation. Set the noise-reduction filter and choose which device runs the transcription model — all without opening a menu. A quick-access hotwords button lets you add domain-specific terms on the fly.

The last transcription is always visible at the bottom, alongside a training card showing how many voice samples you have stored for personal training — click it to browse the full sample list. From here you can open Settings, view History, correct the last transcription, or start recording with a single click. Closing the window hides the app to the system tray, where it keeps running in the background, ready the moment you press your hotkey.

Press, speak, done

Press your hotkey and the app starts listening. A live timer shows elapsed time and how much recording time remains. Release the key — or press again in toggle mode — and the audio is transcribed and typed straight into whatever window has focus.

Transcribe any file — in any language

Transcribe — or transcribe and translate — any audio or video file. Drag and drop or browse to a file, pick a target language if you want a translation, and save the output as a plain-text or SRT subtitle file.

Record and translate live

Transcribe — or transcribe and translate — live microphone input. Record, pick a target language if you want a translation, and save the output as a plain-text or SRT subtitle file.

Capture what plays on your speakers

Transcribe — or transcribe and translate — audio from any output device on your PC, such as your speakers. Capture meeting calls, browser tabs, or any system audio, then save the result as a plain-text or SRT subtitle file.

Translate into many languages at once

For simultaneous multi-language translation, pick the target languages you want to translate into at once and choose how the results are laid out on screen — one per line, inline side-by-side, or first target only.

Translate text and subtitles

Translate any plain text or SRT subtitle file into another language. Your hotwords list applies here too, so brand names and technical terms stay consistent in the translation.

Teach it your vocabulary

The Hotwords dialog lets you feed the AI a list of words it should prioritize — names, technical terms, brand names, or any uncommon vocabulary. Just type a word and press Enter. The model uses these hints during transcription to avoid misrecognizing important terms, and the same list keeps those terms consistent when translating. No retraining required — hotwords take effect immediately.

Fix mistakes, improve the model

The Correct Transcription dialog appears when you tap the Correct button on the main screen. It shows the original transcription alongside an editable correction field. When you save, the corrected text and its matching audio clip are automatically added to your training data — building a personalized dataset that improves the model's accuracy for your voice over time.

Your voice, your dataset

The Training Data window lists every voice sample you have recorded. You can play back any sample, read its transcription, and delete entries you no longer want. These samples form the dataset used when you fine-tune the model to your voice — the more you correct and record, the better it gets at understanding you.

Personalize the AI — on your machine

The Training tab fine-tunes the transcription model on your own voice with LoRA — adapting it to your accent, vocabulary, and speaking style, all without sending data anywhere. One click starts the pipeline: the app automatically picks the NVIDIA CUDA backend when a compatible GPU is present, or falls back to CPU. When training finishes, the result is merged and exported to GGUF so you can switch to your personal model from Settings → Models. Personal voice training is free with every paid licence.

Models & devices

The Models tab is where you manage every model the app uses. Enable word-level timestamps by downloading the optional Forced Aligner, download the translation models, set your defaults, and choose which device the translation model runs on — independently of the transcription engine. Run transcription on one GPU and translation on another, or pin either to CPU.

Full control over input

The Audio tab is where you configure how you interact with the app. Set your recording hotkey from a list of shortcuts, choose between hold-to-record and toggle-record modes, or assign a mouse side button for hands-free control.

A volume slider adjusts input gain, and the text-injection backend can be changed if certain applications don't accept the default typing method. At the bottom, a toggle enables the built-in AI noise reduction powered by DeepFilter — off by default — with an adjustable attenuation slider that controls how aggressively background noise is suppressed.

30 languages + 22 Chinese dialects, one click

The Language tab sets which language the transcription engine listens for. Choose from 30 selectable languages, leave it on auto-detect, or pick Chinese to unlock automatic recognition of 22 regional Chinese dialects. You can also build a list of favorite languages that appear in a quick-switch dropdown on the main screen — perfect if you regularly dictate in more than one language.

Everything you said, searchable

The History tab controls how transcriptions are stored. Enable session history to keep a log that clears when the app closes, or switch to persistent history to save transcriptions across sessions. The Transcription History window shows a timestamped log of everything the app has transcribed, with a Clear History button to wipe it at any time. All history is stored locally on your device.

Make it yours

The Appearance tab lets you choose between a Dark and Light theme and change the interface language. Theme changes take effect after a restart.

Stay up to date

The Updates tab shows your current version, links to the website, and provides contact details for support. A Report a Bug button lets you send feedback directly to the development team. Updates are checked automatically on startup.