NVIDIA
NVIDIA JCA co-generates 3D motion and video for any rig
The NVIDIA Research paper keeps 3D motion in a separate model that handles any skeleton, attached to a pretrained video generator by a few cross-attention layers.
SLOP TV News Desk
UniAVC
UniAVC edits a video and its soundtrack from one prompt
The 19B-parameter model is free to download under the LTX-2 Community License, but it needs about 39 GB of VRAM to run, which rules out consumer GPUs.
HeyGen
HeyGen Video generates picture and sound at $0.02 a second
The model turns one prompt into a 5 to 15 second clip with dialogue, ambience and effects, and HeyGen halves the price through October 31.
deepfakes
How to tell if a video is AI-generated, and where the checks fail
Provenance data, detector models and a court's reliability test each catch different fakes, and the newest research says the pixels alone are getting harder to read.
sarvam
Sarvam pays creators to dub videos into 10 Indian languages
Approved creators get monthly credits to dub their videos through Sarvam Content Studio, plus payment when a promotional video crosses an undisclosed view milestone.
solarrenderer
SolarRenderer turns game-engine block-outs into video in 4 steps
The team froze a 33B MiniMax-H3 video model, added two small LoRAs, and cut sampling from 50 steps to four, with a streaming variant at 768p.
elevenlabs
ElevenLabs ships Eleven Realtime agents answering in 0.57 seconds
Each of the two new speech-to-speech models bundles speech recognition, turn-taking, a language model and a voice into one system, available in ElevenAgents and the Realtime API.
Higgsfield
Higgsfield CLI generates AI images and video from a terminal
The open-source tool signs in through a browser instead of an API key, and charges generations to the same plan credits as the web app.
runway
Runway co-CEO says AI can 'absolutely' replace actors
At View Conference in Turin, Cristóbal Valenzuela also said models cannot yet be directed like a performer, and that they are 'not databases.'
runway
Runway joins Claude Marketplace with Runway Creative
Eligible enterprise customers can apply part of an existing Anthropic commitment to Runway Creative, and neither company has published who qualifies.
nvidia
NVIDIA Cosmos3-H-Dreams generates surgical video at 43.2 fps
The model learned from CMR Surgical Versius gallbladder-surgery recordings and runs on one RTX PRO 6000, but NVIDIA calls it a research simulator.
Mosaic
Mosaic's Motion agent takes on editing and video understanding
The agent cuts, motion-designs and grades video from a brief, then hands back a project you can finish in Premiere, After Effects or DaVinci Resolve.
Tavus
Tavus's Falcon cuts conversation video latency to 430ms
The avatar model generates video one chunk at a time so it can interrupt and react, and Tavus measured a 430-millisecond audio-to-video delay on a B200.
EdenLive
VAST open-sources EdenLive, a real-time video renderer
The 5B model turns rough game footage into detailed frames at more than 24 frames per second on a single RTX 5090; the 14B build runs at 480p.
VideoGen
VideoGen says Model 1 makes 10-minute video from one prompt
The Y Combinator-backed company opened a $1 million credit pool for the model, which it projects will cost more than 50% less than comparable systems.
medeo
Medeo says its Creative OS runs AI video from trend to income
The release describes four stages, discovery, creation, distribution and monetization, and names no price, launch date, customers or usage figures.
kling
Kling 4.0's 30-second clips are not on the API yet
The API pricing page still says its plans don't support Kling 4.0, leaving Runway and Runware to carry Kling 3.0 instead.
ai-video
AI clip of soldiers marching on Indonesia's VP is fake
AFP's fact-check found a SynthID watermark showing Google's AI made the TikTok video, and no credible report of any such Jakarta rally.
artificial-analysis
Artificial Analysis re-based its image-to-video leaderboard
The board now ranks audio-enabled models as AA-Video-I2V v1.1, its Elo values no longer carry over, and Vidu Q4 Preview is missing from it.
fal
FLUX 3 Max's 22x speed claim shrinks to 5.5x on a second chart
fal says the model ties for first on Artificial Analysis's image-to-video board, which lists it second, two Elo points below MiniMax H3.