RESEARCH
Introducing KGV1: Kits.AI’s First Generative Vocals Model
February 18th, 2025
by Kyle Dhillon, Anastasiia Herus, Amantur Amatov
We’re pleased to share our first fully-generative text-to-vocals model: KGV1 (Kits Generative Vocals 1.0).
This model combines elements from SOTA generative music techniques and Kits vocal architectures to produce high quality text-to-vocals generation.
“I’m back in town, put that record on and turn it up.”
“Weathered fences / summer's ended / with my friends and never better.”
“Something about the way you sound / when you sing out of the blue.”
“As I was sleeping on your couch, you woke up to see him out, oh…”
“We will wake up with the sun, cause now we know just who we’re living for”
“This one goes out to the team, without you what would I be”
KGV1 draws on leading research on diffusion transformers to tackle the challenge of lyric conditioning — enabling a diffusion-based system to translate lyrics into cohesive singing.
Beyond that, we’re able to achieve higher fidelity vocal output over other text-to-audio generative models by leveraging modules from Kits Voice Conversion (KVC). Integrating the content encoder, content retrieval, and stable pitch extraction from KVC fixes pronunciation artifacts and pitch inconsistency that are often present in other generative vocal outputs.
Additionally, this gives users control over the timbre and style of their target voice.
The AI Copilot for Your Music Workflow
KGV1 is a starting point for our next generation of powerful generative models that serve the practical needs of music producers. For a vocalist, KGV1 could sketch ideas for top lines; for a producer, it could create unique vocal clips for sampling or use in final production.
From talking with hundreds of producers, artists, and vocalists in the Kits community, we believe generative music tools are most powerful working in the context of a music workflow. As such, future research will move us towards additional musical conditioning signals such as instrumental tracks, pitch curves, MIDI sequences, BPM, and style prompts. We see KGV1 as the first step towards a generative musical intelligence that fits directly into the creative workflow.
KGV1 will soon be available in private beta at app.kits.ai.