DictarDictarGet License — $15
Roadmap

What's shipped.
What's next.

Dictar ships fast. Here's what's live, what we're building, and where we're headed — shaped by what users actually need.

Shipped — v0.1

Shipped
Dictation (Write mode)
Hold a hotkey, speak, release — transcribed and pasted instantly into any text field. Whisper + Parakeet, fully on-device.
Read-aloud (Read mode)
Select any text, press a hotkey — Dictar reads it back with 51 natural-sounding voices. No cloud TTS, all local with Kokoro.
Snippet triggers (Trigger mode)
Type a shortcut like /greet and press Space — it expands into a full paragraph. Supports {date}, {fill}, and AI-drafted expansions.
AI voice commands (Command mode)
Select text, say "make this professional" — Qwen3 rewrites it on-device in seconds. No API key, no uploads.
Global hotkeys
Fully customisable hotkeys for every mode. Works system-wide — any app, any text field, any time.
Custom Modes
Named presets with per-mode settings. Link a mode to an app and Dictar switches automatically when you change windows.
99 languages
Whisper covers 99 languages. Parakeet covers 25 with faster real-time streaming. Pick what fits your workflow.
macOS (Apple Silicon)
Native app for macOS 11+. No GPU required — runs smoothly on any Apple Silicon Mac.

In Progress

In Progress
Windows support
Full feature parity on Windows 10+. x64 build. Targeting release soon.
Improved punctuation
Smarter auto-punctuation, paragraph breaks, and number/date formatting — less clean-up after you speak.

Planned

Planned
Clipboard history
Browse and re-paste previous transcriptions without leaving your workflow.
Audio file transcription
Drag and drop an audio or video file to get a full transcript — processed locally, no upload.
Speaker diarization
Identify and label different speakers in multi-person recordings.
Meeting notes & summaries
Record a meeting and get structured notes with action items — all processed locally.

Exploring

Exploring
Real-time translation
Speak in one language, paste in another. On-device translation paired with transcription.
Personal speech profile
A model that adapts to your voice and accent over time — only possible because everything stays on your device.

Have an idea?

We build what you need. Drop us a feature request and help shape Dictar.

Request a featureGet License — $15