Hey everyone, I’m building a live AI phone receptionist and I’m facing an issue when the assistant has to repeat numbers back to the caller. Problems: • When a caller gives an 11-digit phone number → digits merge or sound unclear • When repeating prices like £1500 → pronunciation sounds distorted • Works fine sometimes, but inconsistent on real phone calls Stack: Vapi + Twilio + n8n + ElevenLabs (also tested Gemini/OpenAI) Tried already : – Increasing end-of-turn timeout (0.5 → 2s) – Changing voices/models/LLMs How do you normally solve this in production systems? Is it formatting, TTS settings, buffering, or another approach?

Real time avatar chat bot that talks to us I am planning to create a real time chatbot that is trained of companies database and it delivers real time conversations and answers as well by speaking . Any ideas on which works better with latency point of view. I have seen few videos using Frontend and backend code and added azurevvoice live api but i am Curious to know if building this on N8N works better for real company data ? any reference links would be appreciated

Hi everyone, I’m trying to use “Create an AI Agent that Writes SQL Queries for You (n8n and MCP)” and I’m looking for a written tutorial. Any help would be greatly appreciated.

I'm setting up a workflow that will update my airtable database if an email comes back undeliverable and delete the email address. No problem. My problem exists if i have more than one email address in the email field, ( randy@myplace.com, randy@wrongplace.com) my search node is not able to find the single bad email address in the database with more than one email. finds it fine with just one email in the email field. Suggestions?

I want to create an agent that can extract plain text from about 100 PDF documents, save the data in a knowledge base database (KB DB), and keep references to the original files. Users should be able to chat with the bot, ask questions about the documents, and receive answers that include links back to the source PDFs. Document Storage: Dropbox AI Model: OpenAI