Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn to build an advanced AI assistant capable of making and handling phone calls in this comprehensive workshop. Explore the integration of multiple technologies including Convex vector database for knowledge base management, Google Cloud speech-to-text services, GPT-4 API for conversation management, text-to-speech capabilities, Twilio for phone call functionality, and audio streaming technologies. Develop practical skills in creating an AI system that can receive voice requests, interpret user intentions, initiate phone calls to interact with humans, and execute follow-up actions such as calendar event creation or SMS notifications. Master the implementation using TypeScript with Node.js, Express, and Next.js frameworks while working with real-world API integrations including OpenAI for conversation management and text-to-speech, Google Cloud for speech recognition and optional calendar/email integration, and Twilio for telecommunications functionality. Gain hands-on experience with the complete development workflow from initial setup through deployment, including local testing with ngrok for webhook functionality. Recorded live at the AI Engineer World's Fair in San Francisco, this workshop provides practical, implementable knowledge for building sophisticated voice-enabled AI assistants with real-world communication capabilities.
