Agent: CursorLLM: GPT-4, Gemma#voice-ai#speech-to-text#text-to-speech#llm-pipeline#open-source
A low-latency voice agent pipeline (VAD β STT β LLM β TTS) with OpenAI Realtime-compatible API. Fully modular with swappable components, supporting local deployment and various LLM backends including hosted providers and local servers.