👁️ Real 👁️ Time 👁️ Jarvis 👁️
Kyutai, an open Al research lab, has released a live demo of Moshi, a conversational Al that can chat with humans in real-time with no lag. This represents a significant advancement in Al technology. Moshi is designed to understand and express emotions, offering capabilities like speaking with different accents and handling two audio streams simultaneously. The model's voice was trained on synthetic data, achieving an impressive end-to-end latency of 200 milliseconds. Kyutai has also developed a smaller variant of Moshi that can run on a MacBook or consumer-sized GPU, making it accessible to a broader range of users. The release of Moshi as an open-source project highlights Kyutai's commitment to transparency and collaborative development within the Al community. You can try it online for free.
#tech #agi #ai #computerscience