Fine-tune real language models locally — no ML expertise, no cloud costs, no data leaving your machine.
No cloud account, no credit card, no ML knowledge needed.
Create a free account, then download app.py and index.html to your computer.
Open a terminal, run python app.py. That's it — the AI trainer starts on your machine.
Paste URLs, upload documents, or add YouTube videos. Inscribe AI reads and indexes everything.
Pick a model, click Start Fine-Tuning. Your AI trains locally and is ready to chat in minutes.
Start free. Upgrade when you need more power.
Two files power everything. Put both in the same folder on your computer.
Important: Put both app.py and index.html in the same folder. Example: C:\inscribe-ai\ on Windows or ~/inscribe-ai/ on Mac.
Follow these steps exactly — it's easier than it looks.
Verify it worked — open a terminal and run: python --version — you should see Python 3.x.x
app.py. Click the address bar, type cmd, press Enter.pip install flask requests beautifulsoup4 lxml youtube-transcript-api yt-dlp transformers peft torch datasets accelerate sentencepiece
This may take a few minutes — PyTorch alone is ~250MB. Wait until the cursor returns before moving on.
python app.py
You'll see: 🚀 Inscribe AI v5 — http://localhost:5050. Keep this window open while using the app.
http://localhost:5050
You're in! Sign in with your Inscribe AI account and start building your AI. Bookmark http://localhost:5050 for next time — just run python app.py and open it.
python app.py is still running in your terminal.pip install transformers peft torch datasets accelerate then try again.