This project provides a free, open-source web application for transcribing and translating audio files using OpenAI's Whisper and Chat APIs. It targets users who need to process audio content, offering a straightforward way to convert speech to text and translate it into different languages.

How It Works

The application leverages OpenAI's Whisper API for transcription and the Chat API for translation. Audio files are uploaded and processed via Laravel's queued jobs. For translation, the VTT output from Whisper is chunked to manage context limits within the Chat API prompts.

Quick Start & Requirements

• Install via git clone https://github.com/beyondcode/writeout.ai.
• Requires an OpenAI account with an API key configured in the .env file as OPENAI_API_KEY.
• No specific hardware or OS requirements are mentioned beyond standard web server capabilities.

Highlighted Details

• Utilizes OpenAI's Whisper API for transcription.
• Employs OpenAI Chat API for translation.
• Implements queued jobs for asynchronous processing.
• Handles VTT file chunking for translation API context limits.

Maintenance & Community

The project is sponsored by "What The Diff". Further community or maintenance details are not provided in the README.

Licensing & Compatibility

The license is not specified in the README.

Limitations & Caveats

The README does not specify the license, which may impact commercial use or closed-source integration. Details on supported audio formats or file size limits are also absent.