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.

34
/ 100
Emerging

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.

conversational-ai speech-technology voice-assistants dialogue-systems knowledge-retrieval
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

28

Forks

3

Language

Python

License

Apache-2.0

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.