Maya 2 Native3B Open-Weight

Low-Latency Streaming TTS • 12 Indian Languages • 20 Personas

Cloudflare Temp Tunnel Connection

Your free Cloudflare tunnel (*.trycloudflare.com) exposes the Tesla T4 Maya2 server to this dashboard without any port-forwarding or public IP setup.

Waiting for Tunnel
Automatic Webhook Sync:/api/tunnel/register

Kaggle T4 Headless CLI & API

30 hrs/week free GPU • Zero browser keeping alive

1-Click API Trigger

Kaggle allows headless background execution via its official REST API. Enter your credentials once to trigger the T4 kernel directly from this dashboard.

Get Key
$ bash notebooks/run_kaggle_cli.sh

Google Colab T4 (CLI & 1-Click)

Tesla T4 16GB VRAM • Colab CLI Authenticated

CLI + Web

Launch directly on Google Colab using your machine's authenticated Colab CLI or run the pre-built notebook in your browser.

# 🚀 1-Line Maya 2 Native T4 Tunnel Launcher
!pip install -q "maya3[server] @ git+https://github.com/MayaResearch/maya2-native" --extra-index-url https://download.pytorch.org/whl/cu128 fastapi uvicorn soundfile requests
!curl -sL https://raw.githubusercontent.com/cloudflare/cloudflared/releases/latest/download/cloudflared-linux-amd64 -o cloudflared && chmod +x cloudflared

# Launch with your current session
DASHBOARD=""
SESSION=""
!python -m maya3.server --ckpt maya-research/maya2-native --host 0.0.0.0 --port 8000 &
!./cloudflared tunnel --url http://127.0.0.1:8000