Reliably transcribe your voice or an audio file on CPU or GPU!

Features

• Voice recording with real-time waveform visualization
• Single file and batch (multi-file) transcription
• Recursive directory scanning for batch processing
• Configurable file type filtering
• Multiple output formats: txt, srt, vtt, tsv, json
• Output to clipboard, source directory, or custom directory
• Real-time system monitoring (CPU, RAM, GPU, VRAM, Power)
• Global hotkey support
• Dockable clipboard and file transcription panels
• All settings persisted between sessions

Supported Models

Uses the faster-whisper library, which provides CTranslate2-based inference for OpenAI's Whisper models. Supports both transcription and translation tasks depending on the model selected.

⚙️ Windows Installer

Download and run FasterWhisperTranscriber_Setup.exe.

💻 Install And Run from Virtual Environment

Download the latest release...unzip and extract...go to the directory containing main.py...run these commands in order:

python -m venv .

.\Scripts\activate

python install.py

python main.py