GitHub Repository

🎙️ Offline voice productivity for Windows - dictate text into any app and control a local AI assistant by voice. Manages notes, to-do lists, appointments & reminders. 100% local: faster-whisper + Ollama + SQLite. No cloud, no telemetry. Free and open source alternative to Wispr Flow

55 starsPython

Writher – offline voice assistant for Windows (Whisper and Ollama)

Name: Writher – offline voice assistant for Windows (Whisper and Ollama)
Availability: InStock
Author: bcorp

by bcorp·Feb 24, 2026·1 point·1 comment

Visit Project View on HN

AI Analysis

●●SolidNiche GemSolve My ProblemShip It

Fully-local Whisper+Ollama voice stack; real Windows app with emoji widget.

Strengths

•Complete offline story: no cloud, no API keys, no telemetry—genuinely addresses privacy concerns.
•Real feature parity: dictation, notes, appointments, reminders with natural-language date parsing.
•Thoughtful UX: system tray integration, animated widget, Windows toast notifications, multi-language support.

Weaknesses

•Early-stage: zero stars on GitHub, no user feedback or real-world validation of accuracy/latency.
•Ollama cold-start and inference time could make assistant mode feel sluggish; no latency benchmarks disclosed.

Similar Projects

AI/ML●●Solid

Local Voice Assistant

This repo bundles a complete local audio loop — client captures audio, backend transcribes with Parakeet, queries a quantized Mistral LLM via Ollama, then renders speech with Kokoro or Qwen3-TTS for cloning — and reports ~1s round-trip on an RTX5070. It’s a practical, take-it-home demo for running privacy-first voice agents, though it’s still a demo: requires specific tooling (Ollama, GPU headroom), has obvious TODOs (VAD, better warmup for cloning), and isn’t reinventing the architecture.

WizardryNiche Gem

armcat

203mo ago

Productivity●●●Banger