FlashLabs Chroma 1.0: A Real-Time End-to-End Spoken Dialogue Model with Personalized Voice Cloning

TL;DR

Chroma 1.0 is an open-source, real-time spoken dialogue system that combines low-latency interaction with high-fidelity personalized voice cloning, improving speaker similarity significantly over previous models.

Contribution

It introduces the first open-source, end-to-end spoken dialogue model capable of real-time operation and personalized voice synthesis with high speaker similarity.

Findings

Achieves 10.96% improvement in speaker similarity over human baseline

Operates with a real-time factor of 0.43, enabling low-latency interactions

Supports multi-turn conversations with high-quality personalized voices

Abstract

Recent end-to-end spoken dialogue systems leverage speech tokenizers and neural audio codecs to enable LLMs to operate directly on discrete speech representations. However, these models often exhibit limited speaker identity preservation, hindering personalized voice interaction. In this work, we present Chroma 1.0, the first open-source, real-time, end-to-end spoken dialogue model that achieves both low-latency interaction and high-fidelity personalized voice cloning. Chroma achieves sub-second end-to-end latency through an interleaved text-audio token schedule (1:2) that supports streaming generation, while maintaining high-quality personalized voice synthesis across multi-turn conversations. Our experimental results demonstrate that Chroma achieves a 10.96% relative improvement in speaker similarity over the human baseline, with a Real-Time Factor (RTF) of 0.43, while maintaining strong reasoning and dialogue capabilities. Our code and models are publicly available at https://github.com/FlashLabs-AI-Corp/FlashLabs-Chroma and https://huggingface.co/FlashLabs/Chroma-4B .