The Runpod Blog

Record 30 minutes of your own speech, fine-tune the open-source F5-TTS model on a Runpod GPU pod, and generate new audio in your voice. Covers dataset prep, training, checkpoint selection, and the F5-TTS license.

Package a small FastAPI service with PyTorch into a Docker image, test it locally on CPU, then deploy it as a private Runpod Pod template with bearer-token auth and verify a real GPU calculation through the HTTP proxy.

How compute became so fragmented, and why software is the answer.

An API tells an agent what it can do, not whether it should. See how skills, a concept graph and live-account tests keep agents right on Runpod.

Put Runpod in the same Terraform plan as the rest of your stack. Deploy your first Pod, let an agent write the plan and migrate from 1.x.

One prompt hands Runpod deploys and cleanup to your coding agent. See install steps for Claude Code, Codex, ChatGPT, Cursor and more, plus a CI path.

Let your coding agent deploy Pods, diagnose failures and shut down what you no longer need, while you decide which actions it takes without asking.