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
- Host: GitHub
- URL: https://github.com/kh4sh3i/media2text
- Owner: kh4sh3i
- License: cc0-1.0
- Created: 2025-07-14T12:42:14.000Z (11 months ago)
- Default Branch: main
- Last Pushed: 2025-07-14T13:05:41.000Z (11 months ago)
- Last Synced: 2026-04-30T16:32:28.558Z (about 1 month ago)
- Topics: ai, api, audio, chatgpt, convertor, deepseek, ffmpeg, media2text, tools, transcription, video, whisper
- Language: Python
- Homepage:
- Size: 91.8 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# ๐๏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.
## ๐ Features
- ๐ Supports audio files: `.mp3`, `.wav`, `.m4a`, `.ogg`
- ๐ฅ Supports video files: `.mp4`, `.mkv`, `.mov` (extracts audio automatically)
- ๐ง Powered by AI models:
- OpenAI Whisper
- DeepSeek (via OpenRouter)
- ๐ง Self-hosted: run locally on your own machine
- ๐ Outputs clean, timestamped text files
## ๐ 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.
## ๐งช Usage
```bash
python media2text.py "path/to/media"
```
## ๐ง Supported Models
| Model | API Support | Offline | Notes |
|-----------|-------------|---------|------------------------------|
| Whisper | โ
Yes | โ
Yes | Best balance of accuracy/speed |
| DeepSeek | โ
Yes | โ No | Requires API key via OpenRouter |
## Tip
for export audio from video file you sohuld install FFmpeg
## ๐ License
MIT License. Use freely, credit appreciated.