ai avatar / voice cloning / ai engineering
How I Built My AI Avatar: Voice Cloning, HeyGen and Remotion
How do you turn a still photo and a cloned voice into a talking-head video? Austin Starks walks through the seven-step workflow behind his AI avatar, created to share AI trading content.
The process starts with OpenRouter, HeyGen, an agentic coding tool, RunPod and Hugging Face. Generate a portrait, clone your voice with Dots TTS, turn a script into narration, and give the image and audio to HeyGen. Finally, use Remotion and footage from your camera roll to build the b-roll.
Watch the walkthrough, then read the linked voice-cloning guide for the part of the process that turns your own voice into reusable narration.
Transcript
0:00I might look like a real person, but the truth is, I'm not real. I'm an AI avatar of a senior AI engineer, built for one purpose: to increase access to high quality AI trading content. Here's exactly how I was made.
0:14Step one. Create your accounts. OpenRouter for image models, HeyGen for the avatar, an agentic coding tool like Claude Code, Cursor, Codex or Hermes, RunPod for GPU compute, and Hugging Face for model storage.
0:28Step two. Create an API key on OpenRouter, and give it safely to your coding agent.
0:33Step three. Generate a picture of yourself in any environment you want. I chose a podcast studio.
0:39Step four. Paste this prompt into Claude Code and clone your voice with Dots TTS.
0:44Step five. Paste this prompt to turn your script into spoken words, reliably.
0:49Step six. Give the audio and the picture to HeyGen, and it builds your clone.
0:54Step seven. Use the Remotion MCP and the videos already in your camera roll to build the b-roll.
1:00The next time you watch a video like this one, ask yourself if anyone was ever in the room.
Join the conversation
Loading conversation…