AI workshop SF: Building Realtime Multimodal AI Agent
Details
Join AICamp and Agora to learn how to create AI agents that can think, listen, see, and interact like humans in real-time!
In this hands-on workshop, you'll explore the TEN framework, experiment with AI services and extensions, and gain the flexibility to build agents for use cases like voice chatbots, AI-generated meeting minutes, language tutors, virtual companions, and more.
Why Attend?
- Learn multimodal AI Agent, OpenAI Realtime API;
- Build your own AI agent from scratch in under an hour;
- Get 1-on-1 consulting and support from the experts;
- Be inspired by live demos showcasing multimodal agents in various scenarios;
- Complete the challenges and win prizes;
- Earn free RTC minutes and contribute to the TEN Agent GitHub repository
Agenda:
- 5:00~5:30pm: Checkin, food and networking
- 5:30~5:50pm: Tech Talk: Multimodal AI agent with the OpenAI Realtime API
- 5:50~6:10pm: Tech Talk: Build voice agent with TEN Framework
- 6:10~8:00pm: Hands-on Workshops
- 8:00: Open discussion, Mixer and Closing.
Speakers/Instructors:
- Plutoless, cofounder of TEN Framework, advocate of RTE Developer Community
- Lengyue, founder of Fish Audio (Hanabi AI Inc.)
Prerequisite:
- Bring your laptop (Minimum system requirements: CPU >= 2 Core; RAM >= 4 GB; Docker / Docker Compose; Node.js(LTS) v18.0.0)
- Keys: OpenAI API key: For the latest Realtime API, feel free to use another provider; for other API like gpt 4o, STT and TTS, we Agora App ID and App Certificate (certificate is not required); Azure SST and TTS API keys (feel free to use another provider).
- More resources to learn before the workshop:
- Visit the TEN Agent DEMO; Check the README on GitHub
Venue:
AWS Loft | San Francisco, 525 Market Street, 2nd Floor, San Francisco, CA 94105
Community on Slack/Discord
- Event chat: chat and connect with speakers and attendees
- Sharing blogs, events, job openings, projects collaborations
Join Slack (search and join the #sanfrancisco channel) | Join Discord
Please register with the below link!
AI workshop SF: Building Realtime Multimodal AI Agent