𝗜𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝗶𝗻𝗴 𝗙𝘂𝗹𝗹-𝗗𝘂𝗽𝗹𝗲𝘅-𝗕𝗲𝗻𝗰𝗵-𝘃𝟯 🚀
Voice agents aren't just chatbots—they need to ACT by using tools 🔨. To feel natural, they must handle your "ums", mid-sentence corrections, and call APIs with low latency.
🧵👇
🚀 Thrilled to release DialogueSidon! Our joint two-speaker dialogue restoration & separation model.
Need full-duplex dialogue data for models like Moshi or PersonaPlex? We've got you covered. 🎙️
👇 Try it with your own samples! https://t.co/2oCdlt3OM0