LiquidCodec runs 361 times faster than real time on one CPU thread, enabling low‑latency audio streaming for Liquid AI's models.
NoteBy OossaPublished by Oossa: 1 min read
Liquid AI announced a new streaming audio codec called LiquidCodec. The codec uses about 74 million parameters and powers the company's LFM3-Audio-2B and LFM3-Omni-2B models. It processes audio at 12.5 Hz with 12 codebooks and can encode roughly 361 times faster than real time on a single CPU thread.
The speed means developers can add low‑latency audio streaming to apps without needing specialized hardware.
Models
The new Gemini 4 Hydrogen model beats the larger Argon on speed, cost and several benchmarks, and is now available to developers and consumers worldwide.
Models
The new Gemini 4 Hydrogen model is now available across Google AI products, offering faster, cheaper and more reliable responses than the previous 3.8 Flash.
Models
Google says the new Gemini 4 Hydrogen model is now live for all Search users, promising deeper understanding, broader link results and richer visual answers.
Oossa · Newsletter
The week in AI, explained
Every Monday: the stories worth knowing, in plain language. Free, no spam.
