awakening-ai/OmniResponse
OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions
Generates real-time multimodal responses (speech, gesture, facial expressions) for interactive conversational agents using LLM backbones with online streaming capabilities. The system leverages the ResponseNet dataset and employs a unified architecture that processes dyadic interaction context to produce synchronized, temporally-coherent outputs across modalities. Supports flexible LLM backbone integration with pretrained model checkpoints planned for distribution.
Stars
12
Forks
—
Language
Python
License
—
Category
Last pushed
Feb 26, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/awakening-ai/OmniResponse"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
stavrostheocharis/auto-streamlit-studio
AutoStreamlit Studio is an intelligent assistant designed to streamline the creation of...
dhineshaps/fetquest-genai
The FET Quest Model Portfolio Project created to explore the Generative AI and Incorporate the...
sitammeur/streamlit-app-builder
A Streamlit-based AI assistant generates custom Streamlit app code from user-provided images or...
grandelli/dfcx-geminiprovision
A Dialogflow CX implementation of a purely determistic agent (intent-based) integrated with...
sitammeur/PicQ
PicQ: Demo for MiniCPM-o 2.6 to answer questions about images using natural language.