Speed Building an AI-Powered Voice-to-Voice Translator with Open-Source Tools

Pre-registration is REQUIRED.
Add to your calendar - https://hubs.li/Q038SfGn0

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!

Speaker: 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.

ODSC Links:
• Get free access to more talks/trainings like this at Ai+ Training platform:
https://hubs.li/H0Zycsf0
• ODSC blog: https://opendatascience.com/
• Facebook: https://www.facebook.com/OPENDATASCI
• Twitter: https://twitter.com/_ODSC & @odsc
• LinkedIn: https://www.linkedin.com/company/open-data-science
• Slack Channel: https://hubs.li/Q038cQBy0
• Code of conduct: https://odsc.com/code-of-conduct/