I'm a YouTuber in San Francisco, and I’ve always struggled to find copyright-safe music for my videos. I wanted something quick and flexible, so I decided to build my own tool.
In about a week, I put together Trymusic AI (https://trymusic.ai), a browser-based music generator. The main feature is the AI Song Generator, which can produce music from text descriptions or moods.
I also added a few extra tools for convenience: Lyrics Generator, BPM Detector, MP3 to MIDI, Jingle / 8-Bit Music Maker, Slowed Reverb Generator
I used Claude Opus 4.5 for stability and 4.6 for more complex prompts. 4.6 has a 1M-token context window, which lets it handle longer or layered instructions better. From what users have noted, it can recall almost all details from long texts, showing clear improvements over 4.5.
I had almost no web dev experience. I used Next.js for the front-end, Vercel for deployment, and claude code to help write and organize code. After seven days of testing, I had a working site where I could generate music directly in the browser.
It's still quite early, but I'd love feedback. I'll be around to answer questions.
No comments yet.
