@leeoxiang: A real-time decision-making model for audio and video—there are so many possible use cases. We put together a few demos to give everyone a feel for them. This will usher in a wave of VoiceAgent and embodied AI applications. https://realtime-omni.dot.cc
Summary
Introduces an online demo site for clef-omni, a real-time audio-video decision-making model. Through eight interactive experiments, the site displays the model’s understanding of audio-video inputs, its decisions, and associated probabilities in real time. The author believes this will help bring VoiceAgent and embodied intelligence applications into practice.
View Cached Full Text
Cached at: 10/11/26, 11:07 AM
A real-time decision-making model for audio and video—the possibilities are so varied that we put together a few scenario demos to give everyone a feel for it.
This will bring a wave of VoiceAgent and embodied AI applications into real-world use.
https://t.co/7ej4lb6dEK https://t.co/ZEpVAuowoh
Audio and Video Real-Time Decision Lab · Try the Decision-Making Model
Source: https://realtime-omni.dot.cc/ AUDIO. VISION. REAL-TIME DECISIONS.
Understand audio and video, decide what to do next in real time.
From conversational turns to visual judgments, observe how clef-omni understands input and chooses actions. Eight interactive experiments show every decision and probability in real time.
One model·Eight online experiences·Real-time probabilities and results
Similar Articles
Cloudflare released Clef-omni, a 30B-A3B decision model that takes audio and video directly (Apache-2.0, Qwen3-Omni base)
Cloudflare 发布 Clef-omni，一个基于 Qwen3-Omni-30B-A3B 后训练的多模态决策模型，可直接接收音频与视频输入，在单次前向传播中输出每个选项的概率，意图路由类基准表现强劲。
@AISuperDomain: Real-time voice agents are moving from "demo toys" to truly usable, and LiveKit Agents is arguably one of the most complete open-source frameworks. It doesn't just chain STT, LLM, and TTS; it also directly provides: • WebRTC real-time audio/video • Inbound and outbound phone calls • …
LiveKit Agents is an open-source real-time voice agent framework supporting WebRTC, telephony integration, semantic turn detection, MCP tool calling, and multi-agent handoff, helping developers quickly build real-time voice applications such as AI customer service and phone bots.
Introducing Clef-omni with full multimodality, plus a faster Clef and a cheaper Clef-flash (7 minute read)
Cloudflare发布开源权重决策模型Clef-omni，支持音频、视频、图像和文本全模态输入，并同时加快了Clef速度、降低了Clef-flash价格。模型基于Qwen3-Omni-30B-A3B-Instruct MoE架构构建，去掉了文本转语音输出组件。
@ycombinator: Tune in:
Koval is a simulation and observability platform for voice agents, helping enterprises scale voice applications safely. Founder Brooke Hopkins shared the potential of voice as a natural interface for AI, as well as the architectural similarities between voice AI and autonomous driving.
Open d1: Edge decision models for text, vision, and audio (6 minute read)
Liquid AI 发布了 d1 决策模型家族的两款开放权重模型 d1-3B 和 d1-omni-600M，支持文本、视觉和音频模态，通过单次前向传递直接输出答案，在 Decision Index 上超越同规模模型并可在 NVIDIA Jetson 边缘设备上实现实时推理。