{"id":"lfm3-audio-2b","slug":"lfm3-audio-2b","name":"LFM3-Audio-2B","orgId":"liquid","family":"lfm3-audio-2b","releaseDate":null,"availability":"announced","openWeights":true,"license":null,"paramsTotal":2000000000,"paramsSource":"slug","contextWindow":null,"knowledgeCutoff":null,"modelCardUrl":"https://www.liquid.ai/blog/lfm3","hfRepo":null,"modalities":["audio","text"],"aliases":["LFM3-Audio-2B","lfm3 audio 2b","lfm3-audio-2b","liquidai/lfm3-audio-2b","lfm3-audio"],"aliasNote":null,"origin":"tracked","tracked":{"trackedSince":"2026-10-27","announced":"2026-10-27","blurb":"Liquid AI's LFM3 audio model for laptops and edge devices. It takes text or audio and answers in text, speech or both: voice chat, speech recognition, synthesis and translation in 18 languages, audio understanding, and tool calls from spoken requests. Open weights under the LFM Open License v1.0.","api":"live","openWeights":"yes","params":{"text":"2B","source":"Hugging Face model card (safetensors: 2,002,332,928)"},"facts":[{"label":"Architecture","value":"LFM3 backbone, in-house causal audio encoder (16 kHz) and LiquidCodec audio tokenizer (24 kHz speech output)"},{"label":"Input / output","value":"Text or audio in; text, speech, or interleaved text and speech out; streaming"},{"label":"Context","value":"32K tokens (input + output)"},{"label":"Speech languages","value":"Arabic, Danish, German, Greek, English (British and American), Finnish, French, Hebrew, Italian, Japanese, Korean, Dutch, Polish, Portuguese, Spanish, Swedish, Turkish, Chinese"},{"label":"License","value":"LFM Open License v1.0"},{"label":"API","value":"Liquid AI API and Playground, per Liquid's blog"}],"claims":["Lab claim: better speech quality than LFM2.5-Audio, with English TTS at UTMOSv2 3.8 and 1.4% WER vs 3.2 and 1.9% for LFM2.5-Audio-1.5B, and time to first token as low as 50 ms."],"sources":[{"kind":"lab","title":"Liquid AI: Introducing LFM3","url":"https://www.liquid.ai/blog/lfm3","date":"2026-10-27"},{"kind":"repo","title":"LiquidAI/LFM3-Audio-2B on Hugging Face","url":"https://huggingface.co/LiquidAI/LFM3-Audio-2B"}],"firstBenchmark":null},"organization":{"id":"liquid","name":"Liquid AI","slug":"liquid","country":null,"url":null,"color":"#1F6FEB","mark":"L"},"price":null,"answer":{"word":"Pending benchmarks.","scope":"Announced Oct 27, 2026; no independent results yet.","lead":"As of Nov 3, 2026, LFM3-Audio-2B is pending benchmarks on isitsota: announced Oct 27, 2026, with no independent results on the boards we track yet.","confidence":"low"},"status":"PENDING_BENCHMARKS","verdicts":[]}