State-of-the-art AI transcription running entirely on your device. No cloud, no subscriptions, no data collection. Fast, accurate, and private.
No credit card required. Works offline after setup.
Professional voice-to-text powered by the Qwen3-ASR engine with GGUF optimization.
Every word you speak is processed locally. Nothing is ever sent to a server. Your data stays on your machine, always.
GPU-accelerated inference with Vulkan for NVIDIA, AMD, and Intel GPUs. Your words appear the moment you finish speaking.
Automatic language detection across 36 languages. Speak in any supported language and the engine adapts instantly.
Download the model once (1.0 – 3.2 GB depending on tier). No internet connection needed after setup.
Fine-tune the model on your voice and vocabulary using LoRA. Not in v1.0 — shipping once our PyTorch-to-GGUF conversion pipeline is ready. Free with Personal and Business licenses.
Perpetual license. No monthly fees, no usage limits, no token counting. One purchase, lifetime access.
DeepFilter AI noise suppression removes background noise in real-time before transcription, improving accuracy in noisy environments.
Transcribed text is typed directly into any application. Works with any text field, code editor, or chat window.
From Fast Light (1.0 GB) to Max Full (3.2 GB). Choose the perfect balance of quality, speed, and resource usage for your hardware.
Six tiers optimized for different hardware. All use the Qwen3-ASR architecture with GGUF quantized decoding.
Maximum accuracy. Zero quality compromise. Best for professional transcription work.
Near-identical quality at reduced size. Ideal for most users with a dedicated GPU.
Large model quality in a compact package. Great for systems with limited VRAM.
Excellent quality from just 1.2 GB. The default tier — great performance on any modern GPU.
Maximum accuracy from the compact model. Perfect when you want speed without quality loss.
The smallest tier. Runs well on integrated GPUs and older hardware.
| Feature | Brethof Voice Pro | Dragon | Google STT | Otter.ai | Whisper (OSS) |
|---|---|---|---|---|---|
| 100% local processing | ✓ | ✓ | ✗ | ✗ | ✓ |
| Perpetual license | ✓ | ~ | ✗ | ✗ | ✓ |
| Native Linux support | ✓ | ✗ | ~ | ✗ | ✓ |
| Native Windows support | ✓ | ✓ | ~ | ✗ | ~ |
| 36 language auto-detection | ✓ | ✗ | ✓ | ~ | ✓ |
| GPU acceleration (NVIDIA + AMD + Intel) | ✓ | ✗ | N/A | N/A | ~ |
| Personal model fine-tuning (coming Q3 2026) | ⌛ | ✓ | ✗ | ✗ | ✗ |
| Built-in noise reduction | ✓ | ✓ | ✓ | ✓ | ✗ |
| Direct text injection | ✓ | ✓ | ✗ | ✗ | ✗ |
| Polished desktop GUI | ✓ | ✓ | ✗ | ✓ | ✗ |
| Typical cost | $49 once | $350+/yr | $17/mo | $17/mo | Free |
No monthly fees. No usage limits. Perpetual license with 1 year of updates included.
No credit card required. Just an email to verify your trial.
Perpetual license. 2 personal devices. 1 year of updates included.
Prices excl. tax. Then $20/year for updates (optional)
Per-seat perpetual license. Team & organization use. 1 year of updates.
Prices excl. tax. Then $20/seat/year for updates (optional)
No. Brethof Voice Pro processes everything locally on your device. No audio or text data ever leaves your computer. There is no cloud component, no telemetry, and no analytics.
Any modern GPU works. NVIDIA GPUs use CUDA acceleration. AMD and Intel GPUs use Vulkan acceleration. You can also run on CPU only, though transcription will be slower. The Fast Light tier (1.0 GB) runs well even on integrated graphics.
Start with Fast Balanced (1.2 GB) — it is the default and offers excellent quality for its size. If you need maximum accuracy for professional work, try Max Full (3.2 GB). If you are on older hardware or want minimal resource usage, try Fast Light (1.0 GB). You can switch tiers at any time from the app settings.
Yes. Brethof Voice Pro supports both Linux and Windows natively. On Linux it works with X11 and Wayland. On Windows it runs as a standard desktop application.
Your license is perpetual — the app keeps working forever with whatever version you have. The optional $20/year Update Pass gives you access to new features and model improvements. Without it, you simply stay on your current version.
Not in v1.0 — but it is coming. Earlier builds had it via PyTorch; when we moved the inference engine to GGUF we had to disable training until the PyTorch-to-GGUF conversion pipeline is production-ready. Target: Q3 2026. It will be free for Personal and Business license holders when it ships, and all training will run locally on your machine. Full roadmap post.
14-day free trial. No credit card. No cloud. No compromises.