🎵 Gomar33

Gomar33 is a voice-driven music production platform built around the concept of "Music at the speed of thought". It helps music lovers and artists eliminate the need of a producer, saving producer costs ($100 - $2,000+) per song.

Users upload or ask for a song to be generated and use natural language to describe modifications in real-time like: "make it a rap song", "make it more like Mozart", "add a saxophone", "slow down the tempo", or "change the pitch".

The technical stack integrates ElevenLabs TTS and ASR/Scribe for voice transcription, with Gemini (Lyria) interpreting commands and applying DSP changes to the song in real-time. The real challenge was making everything seamless - from browser microphone input to voice transcription to audio manipulation.

Built alongside Emmanuel, Adelin, and Eniola.

🥇 This won us first place at the ElevenLabs Global Hackathon (Ireland)!