Loading
Life sciences · Preprint
arXiv · August 12, 2026
Posted before peer review. The findings may change or fail to hold.
CookVoice is a preprint describing an engineering framework for multi-task voice generation (speech, singing, voice conversion, editing) that decomposes voice into content, prosody, and style factors. The authors report comparable quality to existing baselines with 43.51 million parameters and inference requiring as few as 4 ODE steps, but this is an unreviewed technical contribution with no clinical, medical, or human trial evidence.
Preprint.
Framework achieves generation quality comparable to existing Text-to-Speech and text-to-singing baselines while providing stronger style and prosody controllability Model has 43.51 million parameters and achieves efficient inference using as few as 4 ODE steps Supports multiple tasks: text-to-speech, text-to-singing, style-controllable generation, voice mimicry, voice conversion, and voice editing
Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.
The source did not state who this applies to in practice.
This is an unrefereed preprint describing a machine learning framework for voice generation; it reports computational performance and comparative quality metrics but lacks clinical or medical evidence and has not undergone peer review.
Quoted from the source exactly as published.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
Human voice generation has made rapid progress in speech generation, singing voice generation, voice cloning, and voice editing. However, most existing systems are designed for specific tasks and often rely on task-dependent architectures, control signals, or autoregressive decoding, limiting fine-grained controllability and inference efficiency. In this paper, we propose CookVoice, a unified framework for multimodal, multi-style, and multi-task human voice generation. CookVoice decomposes the human voice into three key factors: content, prosody, and style, enabling both speech and singing voice generation within a unified model. To achieve precise and flexible controllability, we design a flexible alignment strategy that maps text, style, and prosody control signals onto the frame-level of spectrogram. This design allows CookVoice to support a wide range of tasks, including text-to-speech, text-to-singing voice, style-controllable generation, voice mimicry, voice conversion, and voice editing. Experimental results show that CookVoice achieves generation quality comparable to existing Text-to-Speech and text-to-singing voice baselines, while providing stronger style and prosody controllability. Moreover, CookVoice achieves comparable performance to large-scale baselines with only 43.51 million parameters and efficient inference using as few as 4 ODE steps, making it a practical solution for real-world human voice generation applications. Demo page is available at https://haoweilou.github.io/CookVoice/.
Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.