Creative ·
How AI built a rap and its own singing voice
Claude wrote a rap about itself, then built the entire song from scratch in TypeScript. No samples, no text to speech APIs, no AI music generators. Even the rapping voice is a speech synthesizer it wrote itself.
In one prompt over about two hours it wrote the lyrics, built every drum and synth from oscillators, mixed and mastered the track, checked the vocals with speech recognition, and drew the music video frame by frame.
Made by u/v3rbxtim. This write-up follows the original post; it is not an independent product test.
Keep up with what gets built.
Read the daily AI briefing, browse the tools, or sign up for briefing email updates.