Multimodal AI
AI models that work across multiple input and output types — text, image, audio, video — within a single pipeline. Multimodal AI is what lets Euryka turn a written brief into an image, then a voiceover, then a video, all carrying the same brand context end to end.
MLLM,multi-modal AI,multimodal learning,multimodal models
On this topic
3 posts reference this topic.
-
Release Note #30: Auto Routing and New Models in Euryka
Meet Auto, the new way to work in Euryka. It routes each message to the right model and keeps conversations consistent. Plus more new models and clearer cost control.
-
The Euryka Release Note #28: Nine New Models and Multi-Model Fan-Out
Nine new models, smarter multi-model comparison, and cost controls — all in one release designed to make AI choice easier, not harder.
-
Euryka Flows: Design Your Entire Campaign on One Canvas
Design your entire creative workflow on one visual canvas. Wire models, branch into variants, merge outputs and save templates that scale—no rebuilding required.