Introduction to Audio Note

Welcome to Audio Note! This guide will help you get up and running quickly.

Product Overview

Audio Note is an AI-powered tool based on OpenAI Whisper that can transcribe your audio into text without an internet connection.

Before getting started, you may want to familiarize yourself with the following concepts:

• OpenAI Whisper: OpenAI Whisper is an open-source speech recognition model developed by OpenAI, designed to provide high-quality speech transcription and translation capabilities. It can convert speech signals into text.
• Audio/Video Files: Audio/Video files are files containing audio and video, which can be in formats such as MP3, WAV, MP4, AVI, etc.
• Subtitle Files: Subtitle files are text files that can be in formats such as SRT, VTT, ASS, etc.
• Real-time Speech Recognition: Real-time speech recognition is a technology that can recognize speech signals in real-time, used in applications like voice assistants and speech recognition.
• Local Translation Models: Local translation models are models that can translate one language into another, used in translation applications.

Features

Audio Note offers the following features (incomplete list):

• Supports transcription of common audio/video files
• Supports real-time microphone transcription and real-time application transcription
• Supports multiple languages (nearly 100 languages)
• Supports official Whisper models and community models
• Supports real-time models (CPU-only, low performance requirements)
• Supports CPU transcription, GPU transcription for most NVIDIA GPUs (CUDA engine), AMD GPUs (Vulkan engine), and Apple M-series chips (CoreML engine)
• Supports various transcription parameter settings for Whisper
• Supports exporting subtitle files in multiple formats
• Supports AI assistants (official AI, OpenAI, Ollama, etc.)
• Supports local translation models and online translation (Google, Bing, etc.)
• More features are under development...

Audio Note takes your data security seriously. Except for downloading models and using online translation, all other operations are completely offline!

Download and Installation

Audio Note supports both Windows and Mac platforms. You can download the appropriate installer for your device here.

Recommended System Requirements

• OS: Windows 10/11, macOS 11+
• CPU: Intel, AMD, Apple M-series chips
• RAM: 8GB+
• Storage: 1GB+
• GPU: Supports NVIDIA GPUs, AMD GPUs, Apple M-series chips
• Internet: Required for downloading models, activation, online translation, AI assistant, and other features

For users without a dedicated GPU, it is recommended to use real-time models for real-time transcription.

Login and Registration

To use Audio Note for the first time, you need to register an account. Click here to log in or register.

After registering and logging in, open the application and click the login button to authorize your account.