← Back to Model Beat
Open Source·Aug 13·all news from August 13, 2026

Marco-Voice Technical Report

Researchers have introduced Marco-Voice, a new speech synthesis system that combines voice cloning and emotion-controlled generation into a single framework. The model aims to improve the expressive quality of synthetic speech by integrating these capabilities into a unified architecture.

Covered by 1 source

  • AarXiv CS.AIFengping Tian, Chenyang Lyu, Xuanfan Ni, Haoqin Sun, Qingjuan Li, Zhiqiang Qian, Haijun Li, Longyue Wang, Zhao Xu, Weihua Luo, Kaifu ZhangAug 13

Related stories

Open SourceChina's Zhipu Says Open-Source GLM-5.3 Outperforms Anthropic's Restricted Model in Vulnerability DetectionAug 14 · 7 sourcesOpen SourceMotif 3: Technical ReportAug 11Open SourceOh Lord, AI Reporters Are Actually Breaking Big NewsAug 12 · 3 sourcesOpen SourceWyvern: An Agentic Framework for Generating Grounded Multimodal ReportsAug 17