Products & SaaS

Wisperflow

May 2026•4 weeks•Rust + Tauri + whisper-rs

Local-first Windows voice dictation tool. Hold a key, speak, and get polished text injected anywhere on Windows.

Wisperflow

Overview

Designed a highly modular, decoupled architecture by defining clear trait contracts for audio capture, STT engine, cleanup rules, and text injection.

Integrated whisper.cpp via whisper-rs for fast, on-device speech-to-text processing without relying on external cloud APIs.

Engineered the Win32 API integration strategy for global hotkey detection and seamless text injection, utilizing modern tooling to handle the low-level hooks.

Key Challenges:

  • •Designing a robust event-handling strategy to accurately manage audio resampling and complex focus-stealing edge cases on Windows.
  • •Structuring the modular pipeline so that underlying engines (like Groq STT vs local LLMs) could be swapped effortlessly without breaking the core system.

Built With

Node.jsJS

Rust

Language

Tauri

Framework

whisper.cpp

AI / STT

Key Features

01

Local-First STT

Runs whisper.cpp models directly on-device, ensuring complete privacy with no cloud audio processing.

02

Global Hotkey

Hold Ctrl+Space from anywhere in Windows to start dictating instantly.

03

Universal Injection

Uses Win32 SendInput and clipboard pasting to inject transcribed text into the currently focused window.

04

Modular Pipeline

Highly decoupled Rust architecture allowing easy swapping of STT models, cleanup rules, and input sources.

05

Audio Capture

Reliable microphone capture using cpal (WASAPI) with automatic resampling.

06

Rules-based Cleanup

Conservative regex and rules engine to polish transcribed text before injection.

Visual Showcase

Wisperflow screenshot 1
Wisperflow screenshot 2
Wisperflow screenshot 3
Wisperflow screenshot 4
Wisperflow screenshot 5

Development Journey

Core Architecture

1 weekMay 2026
  • Defined trait contracts for Transcription, Cleanup, and Injection
  • Set up Cargo workspace and crates structure
  • Implemented cpal audio capture and resampling

Integration

2 weeksMay 2026
  • Integrated whisper-rs for local STT
  • Built Win32 SendInput and clipboard injection
  • Wired global hotkey (Ctrl+Space) listener

Refinement

1 weekMay 2026
  • Added regex-based text cleanup rules
  • Tested pipeline end-to-end via CLI PoC
  • Planned Tauri shell and local-LLM integrations
Open to opportunities

Looking for a Full-Stack Developer?

I'm actively seeking opportunities to join a great team and contribute to exciting products. Drop me a message!