100% Local — Your voice never leaves your machine

Voice to Text That Never Leaves Your Computer

State-of-the-art AI transcription and translation running entirely on your device. Speak in 30 languages, translate to 38 — no cloud, no subscriptions, no data collection.

No credit card required. Works offline after setup.

🔒 100% Local — No cloud ever
🌐 30 ASR + 38 Translation languages
GPU Accelerated — NVIDIA, AMD, Intel
💻 Linux & Windows
✈️ Works Offline

Everything you need, nothing you don't

Professional voice-to-text powered by the Qwen3-ASR engine with GGUF optimization.

🔒

Complete Privacy

Every word you speak is processed locally. Nothing is ever sent to a server. Your data stays on your machine, always.

🌐

30 Languages + 22 Chinese Dialects

Powered by Qwen3-ASR. Lock to a specific language or let the engine auto-detect. 22 Chinese regional dialects recognised automatically.

💬

Offline Translation — 38 Languages New in v2.0.0

Tencent Hunyuan MT2 — translation quality comparable to Google Gemini 3.1 Pro on FLORES-200 (XCOMET-XXL), running entirely on your own machine. Translate any transcription, voice-keyboard output, or SRT/VTT subtitle file.

✈️

Fully Offline

Download the model once (~1–3 GB for ASR, optional ~1 or ~4.3 GB for translation). No internet connection needed after setup.

📈

Two Model Sizes

0.6B for laptops and integrated GPUs, 1.7B for higher accuracy on accented or noisy audio. Switch any time from Settings → Models.

🎓

Personal Voice Training

Fine-tune on your accent with LoRA — runs end-to-end on your machine. Auto-saves corrections from your daily use, auto-exports to GGUF when done. Free with every paid licence.

💰

Pay Once, Own Forever

Perpetual license. No monthly fees, no usage limits, no token counting. One purchase, lifetime access.

🎵

Built-in Noise Reduction

Optional DeepFilter noise suppression for recordings in noisy rooms. Off by default — enable from the Noise popup when you need it.

⌨️

Voice Keyboard + Translation Chip

Hold F9, speak, and the text lands wherever your cursor is. Optional translation chip types the translated text instead — speak in one language, type in another.

Two sizes, your call

Both run the same Qwen3-ASR architecture. Pick once, switch any time from Settings → Models.

1.7B

Large · Vulkan / CPU
~2–3 GB

Higher accuracy on accented or noisy audio. Comfortable on 6 GB+ VRAM. State-of-the-art among open ASR.

Optional add-ons download on demand from Settings → Models:

Forced Aligner (~540 MB) for word-level timestamps · Hunyuan MT2 Fast (~1 GB) or Quality (~4.3 GB) for translation.

How we compare

Feature Brethof Voice Pro Dragon Google STT Otter.ai Whisper (OSS)
100% local processing
Perpetual license ~
Native Linux support ~
Native Windows support ~ ~
30 ASR languages + auto-detect ~
Offline translation (38 languages)
GPU acceleration (NVIDIA + AMD + Intel) N/A N/A ~
Personal model fine-tuning (LoRA)
MCP server for AI agents
Built-in noise reduction
Direct text injection
Polished desktop GUI
Typical cost $49 once $350+/yr $17/mo $17/mo Free

Pay once. Own forever.

No monthly fees. No usage limits. Perpetual license with 1 year of updates included.

Launch Promotion — Limited Time

Save 50% on Personal and 40% on Business licenses. Price locks in at purchase.

Get Launch Price
Free Trial
$ 0
14 days, all features unlocked

No credit card required. Just an email to verify your trial.

  • Both model sizes (0.6B + 1.7B)
  • GPU acceleration
  • 30 ASR + 38 translation languages
  • Noise reduction
  • × No personal training (paid plans only)
  • × No MCP server (paid plans only)
  • × 14-day limit
Start Free Trial
Business
$ 149 /seat
Regular price: $249/seat
⚡ Launch promo — limited time

Per-seat perpetual license. Team & organization use. 1 year of updates.

  • Perpetual license (per seat)
  • Team & organization use
  • Both ASR sizes (0.6B + 1.7B)
  • Offline translation (38 languages)
  • Personal voice training (LoRA)
  • MCP server for AI agents
  • Priority support
  • Volume discounts (10+ seats)
Buy Business License

Prices excl. tax. Then $20/seat/year for updates (optional)

Frequently asked questions

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, AMD, and Intel Arc all use Vulkan acceleration. You can also run on CPU only, though transcription will be slower. The 0.6B model runs comfortably on integrated graphics or any 4 GB+ Vulkan card.

Start with the 0.6B model — it is the recommended default and runs great on most GPUs (and even on CPU on most modern machines). If you need higher accuracy on accented or noisy audio, switch to the 1.7B model (needs 6 GB+ VRAM). You can switch sizes at any time from Settings → Models without re-downloading.

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.

Yes — personal voice training is included in v2.0.0 and runs end-to-end on your machine. Every time you correct a misrecognised word, the {clip, correction} pair is auto-saved to your local training dataset. The main window's training card shows total samples and minutes captured at a glance — click "Start training" in the Training tab to fine-tune a LoRA on your accent. The result auto-exports to GGUF and you switch to it in one click. Free for every paid licence, your voice data never leaves your machine.

Ready to try it?

14-day free trial. No credit card. No cloud. No compromises.

Everything we build

External:   YouTube · GitHub