{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreicy5uipqz7vxqaoi7nx4zkcs6m4vo52v2mu6yxtua2altp22hzjuy",
"uri": "at://did:plc:hktb7775qjyt6dh4h5dilmcp/app.bsky.feed.post/3mklzaorxna52"
},
"coverImage": {
"$type": "blob",
"ref": {
"$link": "bafkreih5j5u3njwl7tnsko4gxabd4udd5hwa6laalhrgdgxearqwdylud4"
},
"mimeType": "image/jpeg",
"size": 346573
},
"path": "/blog/nemotron-3-nano-omni-multimodal-ai-agents/",
"publishedAt": "2026-04-28T16:00:28.000Z",
"site": "https://blogs.nvidia.com",
"tags": [
"AI",
"Agentic AI",
"Artificial Intelligence",
"Nemotron",
"NVIDIA NeMo",
"Open Source"
],
"textContent": "AI agent systems today juggle separate models for vision, speech and language — losing time and context as they pass data from one model to the other. Unveiled today, NVIDIA Nemotron 3 Nano Omni is an open multimodal model that brings these capabilities together into one system, enabling agents to deliver faster, smarter responses with […]",
"title": "NVIDIA Launches Nemotron 3 Nano Omni Model, Unifying Vision, Audio and Language for up to 9x More Efficient AI Agents"
}