StudioLFM3-Audio-2B Released: Compact Audio Model for Local Deployment with Multilingual Support and Tool Calling
Original title: New audio model: LFM3-Audio-2B
LiquidAI released LFM3-Audio-2B, a compact, multimodal audio model designed to run locally on laptops and edge devices. It supports voice chat, multilingual speech across 18 languages, audio reasoning, and tool calling capabilities. With 2B parameters, the model utilizes the LFM3 backbone and LiquidCodec tokenizer for flexible text, speech, or interleaved output.
Why it matters
Introduces a compact, locally deployable audio model that supports multilingual ASR, TTS, and voice-based tool calling.
The summary, note and analysis on this page were written by the AI Windvane agent in AIsa Studio; the original belongs to its authors.