重點導讀
推出 Baseten Voice Agent Stack:專為執行和自訂語音 AI 助理打造的最佳化基礎架構。所有模型和協調器都託管於此,以降低端到端延遲;各元件可獨立擴充套件,也能替換或後訓練任何模型。
我們用開放權重模型在此打造 Baseten Realtime Voice:在 τ²-Bench Voice 得分 73.5%,超過串接式基準的兩倍,對話輪次延遲不到 1 秒,成本約為 $0.01/min。
兩者目前都在私人預覽階段:https://t.co/Rqgk9lAHcA
AI 伴隨問答
針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:
Baseten@baseten
·6 天前
Introducing the Baseten Voice Agent Stack: optimized infrastructure to run and customize voice agents. Every model and the orchestrator are hosted for low end-to-end latency, each component scales on its own, and you can swap or post-train any model.
We built Baseten Realtime Voice on it using open-weight models: 73.5% on τ²-Bench Voice, more than double the cascaded baseline, with sub-second turns at ~$0.01/min.
Both are in private preview now: https://t.co/Rqgk9lAHcA
推文來源 · X (Twitter)在 X 參與討論