LLM-powered speech synthesis and voice chat
5 repos
Python-based systems for building real-time voice interactions by combining large language models with speech-to-speech and text-to-speech synthesis. The cluster centers on practical implementations of conversational AI with audio I/O, often containerized with Docker and leveraging model formats like GGUF. Projects range from prototype speech synthesis pipelines to full voice chat applications with WebRTC integration, representing both the infrastructure and application layer of spoken-language AI.
Python · 3
JavaScript · 1
TypeScript · 1
llm ·100
sst ·88
tts ·88
audio-to-audio ·12
gguf ·12
rag ·12
