Liquid AI releases LiquidCodec, a 74M-parameter streaming audio codec running at 12.5 Hz with 12 codebooks
Liquid AI released LiquidCodec, a streaming audio codec of about 74M parameters. It runs at 12.5 Hz with 12 codebooks and encodes about 361x faster than real time on a single CPU thread. It powers LFM3-Audio-2B and LFM3-Omni-2B.
Liquid AI has released LiquidCodec, a streaming audio codec of about 74M parameters that runs at 12.5 Hz with 12 codebooks, according to a MarkTechPost report published November 12, 2026.
Key specifications
- Parameters: about 74M
- Frame rate: 12.5 Hz
- Codebooks: 12
- Encoding speed: about 361x faster than real time on a single CPU thread
- Mode: streaming
Where it is used
LiquidCodec powers two Liquid AI models: LFM3-Audio-2B and LFM3-Omni-2B.
Pricing and availability
Pricing is not yet disclosed.
What this means
LiquidCodec is the audio component shared by LFM3-Audio-2B and LFM3-Omni-2B, so both models rely on the same codec. The 361x real-time encoding figure on a single CPU thread points to a codec light enough to run without a GPU. The 74M parameter count is small next to the 2B-parameter models it serves.
Related Articles
Google Antigravity adds Gemini 4 Hydrogen and Orchestrator, which switches between Hydrogen and Carbon mid-session
Google is rolling out Gemini 4 Hydrogen in Antigravity, along with Orchestrator, a model option that hands work back and forth between Hydrogen and Gemini 4 Carbon within one session. Google claims Orchestrator used 24% less quota and finished 19% faster than Carbon on Terminal-Bench 4.1 while reaching near-Carbon task success.
Perplexity releases Decider v1.3 and Decider Flash v1.3 with text-span extraction and Apache-2.0 weights
Perplexity released Decider v1.3 and Decider Flash v1.3 on November 12, 2026, adding verbatim text-span extraction and downloadable Apache-2.0 weights. The company reports 91.6% mean accuracy for the larger model across 63 query-classification tasks.
Google launches Gemini 4 Hydrogen: 1M-token context, $1.50 input and $7.50 output per 1M tokens
Google announced Gemini 4 Hydrogen on November 12, 2026, with native 1 million-token input and up to 1 million output tokens. It costs $1.50 per million input tokens and $7.50 per million output tokens, and Google claims it scores 51 on the Artificial Analysis Intelligence Index at its default high thinking level.
Geodesic Intelligence releases NovaAtom-Lite, a biomolecule model it claims tops state-of-the-art systems
Geodesic Intelligence has released NovaAtom-Lite, an AI model that predicts the structures and interactions of biomolecules. Founder Quanquan Gu said the model topped a third-party benchmark in several drug discovery tasks, according to the South China Morning Post.
Comments
Loading...