ictnlp/Stream-Omni

Stream-Omni is a GPT-4o-like language-vision-speech chatbot that simultaneously supports interaction across various modality combinations.

44
/ 100
Emerging

This project offers a sophisticated AI chatbot that can understand and respond using various types of information simultaneously. You can provide text, images, or spoken words, and it will give you answers in both text and spoken form. This tool is ideal for anyone needing real-time, multifaceted communication, such as customer service agents, educators, or researchers.

384 stars. No commits in the last 6 months.

Use this if you need an AI that can interact naturally using a mix of spoken language, text, and visual information at the same time.

Not ideal if your primary need is for a simple text-only chatbot or if you require very specific, highly specialized domain knowledge without multimodal interaction.

AI-chatbots multimodal-communication customer-service-automation interactive-AI voice-assistants
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 17 / 25

How are scores calculated?

Stars

384

Forks

44

Language

Python

License

GPL-3.0

Last pushed

Jun 17, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/ictnlp/Stream-Omni"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.