k
keynews.ai
keynews.ai
FrontierThe story, in brief

New AI model generates 45-minute lip-synced video from one photo and runs in real time

45 minutes of video from a single photo. LPM 1.0 just made real-time lip-sync a commodity.

Reporting by The Decoder 1 min brief
Illustration of a transparent lens revealing connected networks across layers of paper.
Exploring the next frontier of AI research.AI illustration by KeyNews
The KeyNews take

Why it matters

A new capability milestone in video generation—real-time lip-sync and emotional rendering at scale—signals the next frontier in multimodal AI commoditization. This research-to-product pipeline threatens existing video synthesis startups.

The key facts

5 to know

  1. LPM 1.0 generates 45-minute lip-synced video from single image input

  2. Real-time inference capability (runs without batch processing delays)

  3. Includes facial expressions and emotional reactions

  4. Currently positioned as research project, not commercial product

  5. Multimodal video generation capability advancing rapidly

Go to the source

The Decoderthe-decoder.com

Publisher excerpt: A single image becomes a talking character: LPM 1.0 generates real-time video with lip sync, facial expressions, and emotional reactions. For now, it remains a research project.
Read original report
Back to today's editionMore frontier news

The wider picture

View all
Illustration of a transparent lens revealing connected networks across layers of paper.
AI illustration by KeyNews
Frontier01

Alibaba Unveils Zhenwu V900 — and Plans Qwen Models With Up to 10 Trillion Parameters

Alibaba is advancing on two fronts simultaneously: announcing a custom AI accelerator (Zhenwu V900) and committing to massive model scale (10T parameters for future Qwen releases). For practitioners, this matters as a credible third-party capability play outside the US-China licensing squeeze; for enthusiasts, it's a significant lab-race signal about training compute and parameter scaling as competitive levers.

TechRepublic
Illustration of a transparent lens revealing connected networks across layers of paper.
AI illustration by KeyNews
Frontier02

Kyutai Releases Voice of Reason: A Speech-Native Model that Solves Spoken Math with Reinforcement Learning

A new capability frontier: models that reason directly in speech without transcription bottlenecks. This changes how we think about multimodal reasoning and what's possible with open-weight releases at scale.

MarkTechPost
Illustration of a transparent lens revealing connected networks across layers of paper.
AI illustration by KeyNews
Frontier03

Claude Opus 5.5, GPT-6 Sol, GPT-6 Luna, and a new price war

Frontier labs are shipping upgraded reasoning and multimodal models in rapid succession, signaling acceleration in the capability race. Simultaneous price cuts reshape AI economics for practitioners.

Simon Willison