Text to Speech using generated voices

Today I got to implement something unique. I used ElevenLabs to create an artificially generated voice model that was used to generate a voice-over based on whatever text the user types into the field.

The code is on my GitHub if you want to try it out.

I also had one of my best experiences reading the documentation, which is now AI-powered. I can literally ask the agent, "How do I generate a voice?" and the model would respond with the exact code snippet from the documentation.

Next up: creating an AI agent.