Hi everyone,
I’ve set up complex RAG systems where the WhatsApp Business API responds in text, audio, or even with images and documents, and it works well. However, I’ve never worked on a system for handling calls to the Business API number. I’d like to build a call center for interacting with knowledge. This would obviously work best with custom GPT models, as RAG systems tend to have too much latency for real-time interaction.
Does anyone have resources or insights on how to connect calls to the GPT-4o Realtime model or potentially ElevenLabs’ latest real-time models (either option works)?
Thanks in advance!
- n8n version: 1.69.2
- Database (default: SQLite): QLite
- n8n EXECUTIONS_PROCESS setting (default: own, main): own, main
- Running n8n via (Docker, npm, n8n cloud, desktop app): self-hosted in google cloud
- Operating system: Windows10