How Dikt Works

From voice to polished text in seconds. A simple four-step pipeline that runs locally or in the cloud.

The Pipeline

1

Record

Press your global hotkey and start talking. NAudio captures high-quality audio from your microphone in the background, in any application.

2

Transcribe

Your audio is converted to text using Whisper.cpp locally on your machine, or via OpenAI's cloud API for maximum accuracy.

3

AI Cleanup

Optional AI post-processing with Claude or GPT fixes grammar, punctuation, filler words, and applies formatting to your text.

4

Inject

The polished text is automatically injected at your cursor position in whatever application you're using. No copy-paste needed.

Local vs Cloud Transcription

Choose the approach that fits your needs. Use both with automatic failover.

Local (Whisper.cpp)Cloud (OpenAI API)
CostFreePay-per-use
Internet RequiredNoYes
PrivacyAudio stays on deviceAudio sent to OpenAI
AccuracyGood (varies by model)Excellent
SpeedDepends on hardwareFast (server-side)
EngineWhisper.cpp modelsOpenAI Whisper API

Privacy & Security

Your voice data is yours. Dikt is designed from the ground up to keep your information private and secure.

  • DPAPI encryption for all API keys stored on disk
  • No server-side storage of your transcriptions or audio
  • Local-only mode disables all network features entirely
  • No telemetry or analytics collected by default
  • Atomic file writes prevent settings corruption

Whisper Model Comparison

Choose the model that balances speed, accuracy, and disk space for your needs.

ModelSizeSpeedAccuracyBest For
tiny~75 MBFastestBasicQuick drafts, low-resource machines
base~142 MBFastGoodGeneral use with decent hardware
small~466 MBModerateVery GoodBalanced speed and accuracy
medium~1.5 GBSlowerExcellentHigh-accuracy offline transcription
large~2.9 GBSlowestBestMaximum accuracy, multi-language

Ready to Try Dikt?

14-day free trial. No credit card required. All features included.