arXivSanyuan Chen, Min-Jae Hwang, Sho Inoue, Anna Sun, Bokai Yu, David Kant, Dongmin Hyun, Dorian Desblancs, Gregory Antonovsky, Oleg Repin, Peng-Jen Chen, Xutai Ma, Zehai Tu, Juan Pino, Wei-Ning HsuThu, Sep 3, 2026, 8:30 AM PDT
score 16.7
New AI model generates realistic voice dubbing and two-way conversations
Original: Alignment-Free Text-Audiobox for Voice Dubbing and Full-Duplex Dialogue Synthesis
Source: arxiv.org ↗
Writing ELI5 summary…