Technology
Parakeet V3 + ONNX
Uses NVIDIA's Parakeet V3 model optimized for local inference via the ONNX runtime.
On-device AI
PrivaSpeech runs speech recognition directly on your Windows PC using Parakeet V3 AI models. Your voice is processed locally, not on remote servers.
Technology
Uses NVIDIA's Parakeet V3 model optimized for local inference via the ONNX runtime.
Hardware
Works on modern CPUs without a dedicated GPU.
Privacy
After the initial model download, transcription doesn't require internet connectivity.
~465MB download, stored locally on your PC
ONNX Runtime with CPU support
English (general vocabulary)
Windows 10/11, 64-bit
When speech recognition happens on your device, you control where your audio goes. There's no need to trust a third party with potentially sensitive recordings.
On-device processing also means lower latency (no network round-trip) and reliable operation even when internet is unavailable.
The tradeoff: on-device models may be less accurate than the largest cloud models for specialized vocabulary. For most dictation tasks, the difference is manageable with light edits.
Explore the cluster
Use these pages to compare adjacent workflows and understand how each privacy-first use case differs.
Workflow
Show the core Windows setup for microphone, hotkey, local processing, output, and correction.
Offline
Rank for no-internet and offline dictation intent with a dedicated workflow page.
Voice typing
Cover offline voice typing intent for Windows users comparing built-in tools.
Local AI
Explain local inference, model behavior, and on-device speech recognition.
Experience speech recognition that runs on your Windows PC, not in the cloud.