Cover Image for Higgs Audio V3 TTS: How to Build Fast, Modern Voice Cloning

Presented by

SGLang is an open-source high-performance inference framework for LLM, built and maintained by the LMSYS Org. Join our events to learn more!

Hosted By

AI

Higgs Audio V3 TTS: How to Build Fast, Modern Voice Cloning

SGLang Meetups and Events

YouTube

Past Event

Welcome! To join the event, please register below.

You will be asked to verify token ownership with your wallet.

About Event

📣 Higgs Audio V3 TTS: How to Build Fast, Modern Voice Cloning

SGLang Office Hours is back!

This week we're joined by Ke and Huapeng from the Boson AI team to talk about Higgs Audio V3 TTS and how to build fast, modern voice cloning that actually sounds human, and their work optimizing SGLang-Omni for TTS production serving!

Higgs Audio V3 isn't built to read text aloud, it's built to speak. It's a text-to-speech model designed for live voice AI, with zero-shot voice cloning from a short audio reference and inline control over emotion, style, speed, pitch, pauses, and sound effects right from the text stream.

Bring your questions for Ke and Huapeng!

Join SGLang Slack 👉 slack.sglang.ai
Follow us on X 👉 x.com/lmsysorg & x.com/sgl_project

If SGLang has been useful to you, a star goes a long way and keeps the team motivated. Let's gooooo ⭐ github.com/sgl-project/sglang

Presented by

SGLang Meetups and Events

SGLang is an open-source high-performance inference framework for LLM, built and maintained by the LMSYS Org. Join our events to learn more!

Hosted By

AI