热点
"实时" 相关文章
Kyutai Releases 2B Parameter Streaming Text-to-Speech TTS with 220ms Latency and 2.5M Hours of Training
MarkTechPost@AI 2025-07-05T08:30:50.000000Z
Kyutai Open Sources Moshi: A Real-Time Native Multimodal Foundation AI Model that can Listen and Speak
MarkTechPost@AI 2024-07-03T19:31:59.000000Z