SoulX-Singer: Towards High-Quality Zero-Shot Singing Voice Synthesis
It addresses the need for practical, flexible SVS systems in real-world production workflows, though it appears incremental by building on existing SVS methods.
The paper tackles the problem of robust and high-quality zero-shot singing voice synthesis (SVS) for industrial deployment by introducing SoulX-Singer, an open-source system trained on over 42,000 hours of vocal data that achieves state-of-the-art synthesis quality across Mandarin Chinese, English, and Cantonese.
While recent years have witnessed rapid progress in speech synthesis, open-source singing voice synthesis (SVS) systems still face significant barriers to industrial deployment, particularly in terms of robustness and zero-shot generalization. In this report, we introduce SoulX-Singer, a high-quality open-source SVS system designed with practical deployment considerations in mind. SoulX-Singer supports controllable singing generation conditioned on either symbolic musical scores (MIDI) or melodic representations, enabling flexible and expressive control in real-world production workflows. Trained on more than 42,000 hours of vocal data, the system supports Mandarin Chinese, English, and Cantonese and consistently achieves state-of-the-art synthesis quality across languages under diverse musical conditions. Furthermore, to enable reliable evaluation of zero-shot SVS performance in practical scenarios, we construct SoulX-Singer-Eval, a dedicated benchmark with strict training-test disentanglement, facilitating systematic assessment in zero-shot settings.