Liquid AI releases LiquidCodec streaming audio codec
Start here
Liquid AI released LiquidCodec, a roughly 74M-parameter streaming speech tokenizer that powers its LFM3-Audio-2B and LFM3-Omni-2B models, with weights published on Hugging Face. The codec compresses 24 kHz audio into 12 token streams at 12.5 Hz frames and runs on a single CPU thread; Liquid AI reports about 361x real-time encoding and 87x decoding, tested on an Apple M4 Max laptop in FP32. It also runs on CUDA GPUs via Transformers and has Q4_0, Q4_K_M and Q8_0 GGUF builds for llama.cpp, loading through Transformers with trust_remote_code=True. Liquid AI says LiquidCodec beat X-Codec 2, NanoCodec and Mimi on ViSQOL and mel distance across all 8 test sets, though NanoCodec still led PESQ (WB) on 7 of 8 sets.
Generated from reports · updated 15 h ago
Report timeline
Follow the reports to see the event from different sides.
- MarkTechPostLiquid AI Releases LiquidCodec, a 74M-Parameter Streaming Audio Codec
Liquid AI released LiquidCodec, a roughly 74M-parameter streaming speech tokenizer that powers its LFM3-Audio-2B and LFM3-Omni-2B models, with weights published on Hugging Face. The codec compresses 24 kHz audio into 12 token streams at 12.5 Hz frames and runs on a single CPU thread, where Liquid AI reports about 361x real-time encoding and 87x decoding. Liquid AI says it beat X-Codec 2, NanoCodec and Mimi on ViSQOL and mel distance across all 8 test sets, though NanoCodec still led PESQ (WB) on 7 of 8 sets.
Heat for this event
Not enough continuous observations yet to draw a trend.