llm-council: LLM Council is a multi-LLM deliberation system that enables multiple large language models to collaboratively answer questions through a three-stage process: independent responses, anonymous peer review, and chairman synthesis. It supports various LLM gateways and can be deployed as a Python library, MCP server, or HTTP API. Designed for high-quality, balanced answers with features like rubric scoring, bias auditing, and offline mode.; FunASR: FunASR is a fundamental end-to-end speech recognition toolkit. It offers industrial-grade speech recognition, being 170x faster than Whisper, supporting over 50 languages, and integrating features like speaker diarization, emotion detection, and streaming.
Complex reasoning and decision-making requiring diverse AI perspectives
Meeting transcription with speaker labels, timestamps, and punctuation