Description

AI agents are revolutionizing automation and real-time communication—but how fast can you build one? In this hands-on session, we’ll rapidly develop a real-time voice-to-voice translator using open-source tools, walking through every step from speech recognition to translation and voice synthesis. 

Designed for AI practitioners and engineers, this interactive workshop will cover: 

- Speech-to-text processing with open-source models 

- Language translation using LLM-powered tools 

- Speech synthesis for real-time responses 

- Optimizing latency for seamless interaction 

- Deploying with open-source frameworks and APIs 

We’ll demonstrate a live build, with attendees coding alongside us. A GitHub repo will be provided for reproducible learning. Whether you're new to AI automation or refining your prototyping skills, you’ll leave with a functional AI agent and the tools to iterate further. 

Bring your laptop, and let’s build!


Local ODSC chapter in NYC, USA

Instructor's Bio

Grace Deng 

Software engineer at GMI Cloud 

She is working on AI infrastructure and inference platforms. She focuses on optimizing inference efficiency and building scalable AI systems and is currently developing a platform for hosting and managing inferencing. Passionate about Gen AI, she aims to empower the community to rapidly prototype and deploy creative AI-driven tools.

Webinar

  • 1

    ON-DEMAND WEBINAR: "Speed Building an AI-Powered Voice-to-Voice Translator with Open-Source Tools"

    • Ai+ Training

    • Webinar recording