Heidelberg AI News

Article · MarkTechPost ·

Liquid AI Releases LiquidCodec, a 74M-Parameter Streaming Audio Codec

Liquid AI released LiquidCodec, a ~74M-parameter streaming audio codec that powers LFM3-Audio-2B and LFM3-Omni-2B. It runs at 12.5 Hz with 12 codebooks and encodes about 361x faster than real time on a single CPU thread.

Read at marktechpost.com The opening of the article at marktechpost.com.

In this story

A tool or model opens in the Heidelberg AI Curriculum: what it does, what it costs, how to start. A repo opens on GitHub.

Related stories

All stories

OfficialHugging Face

Build specialized multimodal models with LFM3

This Hugging Face page presents LFM3, a family of specialized multimodal models from Liquid AI. It lists several LFM3 model variants—Text Generation (8B and 2B), Any-to-Any (2B), and Image-Text-to-Text (2B and 3B)—and links to a collection of base and post-trained LFM3 models hosted at liquid.ai/blog/lfm3. Related posts from the same author cover running private agents on-device with LFM2.5-24B-A2B and multimodal open decision models for the edge.