Model Releases

Liquid AI Releases LFM2-Audio-1.5B End-to-End Audio Foundation Model

Original title:LFM2-Audio: An End-to-End Audio Foundation Model

AI summary

Liquid AI released LFM2-Audio-1.5B, an end-to-end foundation model supporting audio and text input and output, expanding the LFM2 family.

Key Takeaways

  • Liquid AI released LFM2-Audio-1.
  • an end-to-end foundation model supporting audio and text input and output
  • expanding the LFM2 family.

Quick Facts

Published
Updated
Source
Liquid AI 模型与工程博客(网页)
Category
Model Releases
AI score
64
Read the original Read the full article at the original source
Why it matters

官方给出了 VoiceBench、ASR 词错率和低于 100ms 的延迟数据,读者可以据此评估 1.5B 参数模型在端侧实时语音场景的可用性。

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: Liquid AI Releases LFM2-Audio-1.5B End-to-End Audio Foundation Model. October 1, 2025. https://new.nat6.net/en/news/cmtym3yoz000lronzvh6f1gh7/

View all →