Syllablaze v0.4 beta

Real-time audio transcription app using OpenAI's Whisper.

Originally created by Guilherme da Silveira as "Telly Spelly".

Features

• One-click recording from system tray
• Live volume meter
• Microphone selection
• Auto clipboard copy
• Native KDE integration
• In-memory audio processing (no temporary files)
• Direct 16kHz recording for improved privacy and reduced file size

What's New in v0.4 beta

• use Faster Whisper

What's New in v0.3

• Enhanced Privacy: Audio is now processed entirely in memory without writing to disk at any point
• Improved Performance: Direct 16kHz recording reduces processing time and memory usage
• Better Security: No temporary files means no risk of sensitive audio data being left on disk
• Reduced Resource Usage: Streamlined audio processing pipeline for more efficient operation
• Improved Recording UI: Enhanced recording window with app info, settings display, and larger stop button

Screenshots

tray icon:

click on the tray icon opens speech recognition:

notification after action:

text automatically lands into clipboard:

settings screen:

Project Structure

• blaze/ - Core application files
• docs/ - Documentation files
• install.py - Installation script
• uninstall.py - Uninstallation script

Installation

Prerequisites

Ubuntu/Debian

sudo apt update
sudo apt install -y python3-pip python3-dev portaudio19-dev python3-pipx

Fedora

sudo dnf install -y python3-libs python3-devel python3 portaudio-devel pipx

Install

git clone https://github.com/PabloVitasso/Syllablaze.git
cd Syllablaze
python3 install.py

Usage

1. Launch "Syllablaze" from application menu
2. Click tray icon to start/stop recording
3. Transcribed text is copied to clipboard

Configuration

Right-click tray icon → Settings to configure:

• Input device
• Whisper model
• Language

Uninstall

python3 uninstall.py

or

pipx uninstall syllablaze

Requirements

• Python 3.8+
• KDE Plasma

License

MIT License