An open API service indexing awesome lists of open source software.

https://github.com/kh4sh3i/media2text

Convert audio and video files into accurate text transcripts using AI
https://github.com/kh4sh3i/media2text

ai api audio chatgpt convertor deepseek ffmpeg media2text tools transcription video whisper

Last synced: about 1 month ago
JSON representation

Convert audio and video files into accurate text transcripts using AI

Awesome Lists containing this project

README

          










# ๐ŸŽ™๏ธ media2text (AI Audio & Video Transcriber)

Convert audio and video files into accurate text transcripts using AI (Whisper, DeepSeek, or OpenRouter models).
Supports multiple formats and can be self-hosted with minimal setup.

## ๐Ÿš€ Features

- ๐Ÿ”Š Supports audio files: `.mp3`, `.wav`, `.m4a`, `.ogg`
- ๐ŸŽฅ Supports video files: `.mp4`, `.mkv`, `.mov` (extracts audio automatically)
- ๐Ÿง  Powered by AI models:
- OpenAI Whisper
- DeepSeek (via OpenRouter)
- ๐Ÿ”ง Self-hosted: run locally on your own machine
- ๐Ÿ—‚ Outputs clean, timestamped text files

## ๐Ÿ›  Installation

```bash
git clone https://github.com/kh4sh3i/media2text.git
cd media2text
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
pip install -r requirements.txt
```

Create your `.env` file (based on `.env.example`) and add your API keys if needed.

## ๐Ÿงช Usage

```bash
python media2text.py "path/to/media"
```

## ๐Ÿง  Supported Models

| Model | API Support | Offline | Notes |
|-----------|-------------|---------|------------------------------|
| Whisper | โœ… Yes | โœ… Yes | Best balance of accuracy/speed |
| DeepSeek | โœ… Yes | โŒ No | Requires API key via OpenRouter |

## Tip
for export audio from video file you sohuld install FFmpeg

## ๐Ÿ“„ License

MIT License. Use freely, credit appreciated.