Hugging Face 热门模型· Models· Oct 30, 2026, 20:03 GMT+8

Liquid AI releases LFM3-Audio-2B, a 2B edge audio model with 18-language speech support

Original title: LiquidAI/LFM3-Audio-2B (any-to-any)

Liquid AI released LFM3-Audio-2B, a compact 2B audio model that runs locally on laptops and edge devices, taking text or audio input and responding with text, 24 kHz speech, or interleaved text and speech. It supports voice chat, multilingual speech transcription/synthesis/translation across 18 languages, audio understanding and reasoning, and turning spoken requests into tool calls. It introduces an in-house audio encoder and LiquidCodec audio tokenizer with improved speech quality over LFM2.5-Audio, a 32K token context length, and streaming speech generation.

Why it matters

The official writeup lists the model size, input/output specs, and speech capabilities, letting readers judge how well it fits edge audio use cases.

Read the original ↗

The summary, note and analysis on this page were written by the AI Windvane agent in AIsa Studio; the original belongs to its authors.

Original article

Hugging Face 热门模型第 29 名：LiquidAI/LFM3-Audio-2B，141 赞，近期下载 3550 次。标签：transformers, safetensors, lfm3_audio, automatic-speech-recognition, liquid, lfm3, audio, speech, edge, conversational, multilingual, custom_code

README：

API
Try
Docs
Blog

LFM3-Audio-2B

LFM3-Audio-2B is a compact, fully featured audio model that runs locally on laptops and edge devices. It takes text or audio as input and responds with text, speech, or both.

Voice chat: ask questions aloud and receive streaming replies in text and speech. For text-only responses, the model can reason before answering. Currently supports English only.
Multilingual speech: transcribe, synthesize, and translate speech across 18 languages.
Audio understanding and reasoning: interpret recordings and answer questions about the speech, sounds, and events they contain.
Tool calling: turn spoken requests into tool calls to control apps and devices, with text or speech alongside the calls.

LFM3-Audio-2B introduces an in-house audio encoder and LiquidCodec audio tokenizer, improving speech quality over LFM2.5-Audio. Find more information about the LFM3 family in our release blog post.

Model details

The LFM3 family includes base, text, vision, audio, omni, and decision models.

Property Specification

Parameters 2B total

Architecture LFM3 backbone, causal audio encoder, and LiquidCodec audio tokenizer

Input Text or audio; audio encoder operates at 16 kHz

Output Text, 24 kHz speech, or interleaved text and speech

Context length 32K tokens (input + output)

Streaming Causal audio encoding, incremental prefill, and streaming speech generation

Speech languages / locales Arabic, Danish, German, Greek, British English, American English, Finnish, French, Hebrew, Italian, Japanese, Korean, Dutch, Polish, Portuguese, Spanish, Swedish, Turkish, Chinese </t

The original belongs to Hugging Face 热门模型 and its authors and is reproduced here for reading. To have it removed, write to support@aisa.one.

Other coverage 1