Liquid AI releases LiquidCodec audio codec
Understand this story
Liquid AI released LiquidCodec, a streaming speech tokenizer with about 74M parameters, for its LFM3-Audio-2B and LFM3-Omni-2B models, with weights uploaded to Hugging Face. The codec can be loaded via Hugging Face Transformers with trust_remote_code=True; Liquid AI says it can run on a single CPU thread (tested in FP32 on an Apple M4 Max laptop) and also supports running on CUDA GPUs via Transformers. For edge use, Liquid AI lists Q4_0, Q4_K_M, and Q8_0 GGUF versions for llama.cpp.
AI overview based on source reports · Updated 2 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- MarkTechPostLiquid AI Releases LiquidCodec, a 74M-Parameter Streaming Audio Codec
Liquid AI released LiquidCodec, a ~74M-parameter streaming speech tokenizer used in its LFM3-Audio-2B and LFM3-Omni-2B models, which converts 24 kHz audio into 12 token streams at 12.5 Hz frames and back. Liquid AI reports best ViSQOL and lowest mel distance on all 8 test sets versus X-Codec 2, NanoCodec and Mimi, with encode RTF 0.0028 and decode RTF 0.0115 on a single CPU thread, though NanoCodec scored higher PESQ (WB) on 7 of 8 sets. Weights are on Hugging Face, with Q4_0, Q4_K_M and Q8_0 GGUF builds for llama.cpp.
Activity for this story
- Current comparable activity
- 3
- Peak comparable activity
- 10Nov 13 07:00
- Change in the past 24 hours
- -50%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.