Mini-Omni-Reasoner: a real-time speech reasoning framework that interleaves silent reasoning tokens with spoken response tokens (“thinking-in-speaking”), exploiting the LLM–audio throughput gap to keep speech fluent and low-latency while maintaining structured internal reasoning.
☆161Aug 26, 2025Updated 7 months ago
Alternatives and similar repositories for Mini-Omni-Reasoner
Users that are interested in Mini-Omni-Reasoner are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆40Mar 7, 2025Updated last year
- simple web ui to manage mcp (model context protocol) servers in the claude app☆103May 16, 2025Updated 11 months ago