Privacy-First Voice Transcription
FlowSTT is a free, privacy-first speech-to-text application that runs entirely on your local machine. No subscriptions, no signups, no cloud services —- your voice data never leaves your computer.
The main window displays a timestamped history of transcriptions, giving you a running log of everything captured in your session.
A compact voice activity indicator shows a live waveform in the title bar so you always know when FlowSTT is actively listening.
Each transcription entry surfaces play, copy, and delete controls on hover, letting you replay audio, copy text, or clean up entries in one click.
Features
Privacy-First
All audio processing and transcription happens locally. No data ever leaves your machine. No subscriptions, no signups, no cloud services.
Cross-Platform
Native audio backends for each OS: WASAPI on Windows, PipeWire on Linux, CoreAudio and ScreenCaptureKit on macOS.
Hardware Accelerated
NVIDIA CUDA on Windows and Linux, Apple Metal (M-Series) on macOS. Falls back to CPU when no GPU is available.
Echo Cancellation
WebRTC AEC3 algorithm removes speaker feedback when capturing both microphone and system audio simultaneously.
Getting Started
System Requirements
- Windows 10+
- macOS 12.3+
- Linux (coming soon!)
- Optional: NVIDIA GPU (CUDA) or Apple Silicon (M-Series) for accelerated transcription
Installation
Download the latest release for your platform: