the-bird-F/GLM-Voice-RAG
[EMNLP 2025 Findings] A complete cross-modal RAG system for end-to-end speech-to-speech large models, including ASR-based Retrieval and E2E Retrieval.
This project helps developers integrate advanced speech-to-speech dialogue capabilities into their applications, particularly for complex question-answering tasks. It takes raw speech input and, by leveraging external knowledge, generates relevant spoken responses. This is ideal for developers building voice assistants, interactive customer support systems, or educational tools that need to provide informed verbal answers.
No commits in the last 6 months.
Use this if you are a developer looking to build a conversational AI system that can understand spoken questions and provide spoken answers, enhanced by external knowledge retrieval, without relying on traditional text-based intermediate steps.
Not ideal if you are looking for a pre-built, end-user application or a simple API for basic speech-to-text or text-to-speech without the need for complex, knowledge-augmented dialogue.
Stars
28
Forks
3
Language
Python
License
Apache-2.0
Category
Last pushed
Jul 11, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/the-bird-F/GLM-Voice-RAG"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
illuin-tech/colpali
The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.
AnswerDotAI/byaldi
Use late-interaction multi-modal models such as ColPali in just a few lines of code.
jolibrain/colette
Multimodal RAG to search and interact locally with technical documents of any kind
nannib/nbmultirag
Un framework in Italiano ed Inglese, che permette di chattare con i propri documenti in RAG,...
OpenBMB/VisRAG
Parsing-free RAG supported by VLMs