Vyvoice: Privacy-first, cross-platform, offline voice transcription app

Name: Vyvoice: Privacy-first, cross-platform, offline voice transcription app
Availability: InStock
Author: recursivegirth

by recursivegirth·May 16, 2026·2 points·0 comments

Visit Project View on HN

AI Analysis

●●SolidSolve My ProblemCozy

Finally, a real offline dictation tool that actually runs on Windows and Linux.

Strengths

•Fills a genuine gap for non-Mac users tired of Dragon or cloud-only tools.
•ONNX runtime ensures broad hardware compatibility without heavy GPU dependencies.
•Custom VAD loop optimizes processing by ignoring silence segments locally.

Weaknesses

•Local Whisper models often lag behind cloud APIs in raw accuracy and speed.
•Voice command parsing locally is notoriously brittle compared to server-side LLMs.

Post Description

Hey Hacker News,

vyvoice is a cross-platform, offline voice transcription app I started working on in December as a Windows user tired of every good dictation app being Mac-only.

Beyond transcription, it has built in support for voice commands & gen-AI agents (work-in-progress). Windows, Linux, and macOS are currently supported. The primary product is free, agentic AI and other future premium features will be behind a subscription ($5/month).

Underneath the hood vyvoice leverages ONNX to provide transcription via Parakeet and Whisper models locally on the device. I've developed an efficient VAD loop to ensure only segments of audio that contain speech are being processed for transcription. Valid audio segments are decoded in real time with end of utterance. Your audio and transcripts never leave your device.

I would love feedback on all aspects from default settings to commands and agent functionality. I am actively working on the agent feature and plan to support skills, MCP, and more in the very near future. Check it out and let me know what you think!

Check vyvoice out! https://vyvoice.com