Voice & Memory.
A realtime voice assistant with persistent memory and tools for calendar, CRM, and search.
DOCUMENTED OUTCOMERealtimeWhisper · GPT-4o · ElevenLabs
TECHNOLOGIES
Python · Whisper · GPT-4o · ElevenLabs · LangChain · Google Cloud Run
The problem
A useful voice agent needs to respond quickly, retain context, and take action through external tools within the same interaction.
The engineering
01
Connected Whisper speech-to-text, GPT-4o, and ElevenLabs text-to-speech in a realtime voice agent.
02
Added persistent vector-store memory and multi-tool orchestration across calendar, CRM, and search APIs.
03
Deployed on Google Cloud Run with CI/CD.
The outcome
Delivered a deployed realtime voice agent with persistent memory and tool orchestration across calendar, CRM, and search.
PROJECT SUMMARY BASED ON MY RÉSUMÉ. DIAGRAMS ILLUSTRATE THE ARCHITECTURE; THEY ARE NOT PRODUCT SCREENSHOTS.
NEXT PROJECT / 01Nucel