:audio-transcribe

[REAL-TIME] AI-powered transcription

Convert speech to text instantly with OpenAI Whisper. Cross-platform desktop app with <3 second latency, privacy-focused local processing, and beautiful modern interface.

Download Now View on GitHub
Audio Transcribe
Hello, welcome to Audio Transcribe!
|
Connected • Whisper Tiny
Latency: 1.2s
↓

Powerful Features

Everything you need for professional real-time transcription

[MIC]

Real-time Transcription

Live audio to text conversion with less than 3 second latency. Perfect for meetings, interviews, and live events.

[SYS]

Cross-platform

Native desktop applications for Windows, Linux, and macOS. Consistent experience across all platforms.

[AI]

AI-powered

Powered by OpenAI's Whisper model for exceptional accuracy. Optimized "tiny" model balances speed and precision.

[SEC]

Privacy First

Complete local processing. Your audio never leaves your device. No cloud dependencies, no data collection.

[PWR]

High Performance

Optimized for real-time processing with minimal resource usage. Runs smoothly on modern hardware.

[LNG]

Multi-language

Supports multiple languages including English, Spanish, and more. Automatic language detection available.

Interface

Terminal-style web interface for real-time transcription

Main Interface

Web interface with real-time transcription display

Get Started

Choose your preferred installation method

[WIN] Windows

Download the native Windows installer (.bat) or direct executable (.exe).

curl -O https://github.com/JahazielHernandezHoyos/audio-transcribe/releases/latest/download/AudioTranscribe-Windows-Installer.bat


Download Installer (.bat) Download Executable (.exe)

[NIX] Linux / macOS

One-command installation that automatically detects your system and installs dependencies.

curl -sSL https://raw.githubusercontent.com/JahazielHernandezHoyos/audio-transcribe/master/unix_installer.sh | bash


Download Portable

[SRC] From Source

Build from source for development or customization.

git clone https://github.com/JahazielHernandezHoyos/audio-transcribe.git cd audio-transcribe curl -LsSf https://astral.sh/uv/install.sh | sh uv sync python start_app.py


View Repository