New models and features in AI image, video, voice and music generation, from Midjourney, Sora, Veo, Suno and more.
Entertainment firm Hallwood Media just signed Xania Monet to a multimillion-dollar record deal following rapid chart success. Created by a poet who uses Suno to produce music around her lyrics, the artist recently topped the Billboard R&B Digital Song Sales chart and logged 9.8 million U.S. streams.
Kling AI just rolled out a new Avatar feature, integrating an upgraded version of its popular Lip Sync tool directly into the module. The update aims to make talking-head videos look much more natural. It is rolling out with limited access for now.
Udio just rolled out Voices, a new tool giving creators tighter control over song vocals. You can now pick from a curated library of pre-loaded vocal styles or extract and save the voice from a generated track to reuse across future songs. It is free for everyone for two weeks before moving behind the paywall.
Microsoft's Copilot Labs just launched Scripted mode for audio generation, powered by the new MAI-Voice-1 model. It reads your input verbatim instead of improvising, alongside an Emotive mode for added drama and a Story mode that performs multiple characters.
Stability AI just launched Stable Audio 2.5, an enterprise-grade audio generation model capable of pumping out 3-minute tracks in under two seconds. Built on fully licensed datasets for commercial safety, it introduces audio inpainting and dynamic song structures to help brands craft customized sound identities at scale.
ByteDance just launched Seedream 4.0, a new AI image model with native 4K support and fast image editing, directly challenging Google DeepMind's viral Nano Banana. It merges text-to-image with SeedEdit capabilities while boosting inference speeds by over 10x, and is now live across Jimeng, Doubao, and Krea AI.
OpenAI is backing an animated feature film called Critterz to prove generative AI can slash cinema production costs and timelines. Built primarily with AI tools like GPT-5, the project is reportedly being made in nine months for under $30 million with partners Native Foreign and Vertigo Films, targeting a 2026 theatrical release.
Google just updated Veo 3 and Veo 3 Fast, bringing lower pricing across the board alongside new support for 9:16 vertical video and 1080p HD outputs. Both video generation models are now marked production-ready in the Gemini API and continue to include SynthID watermarking.
Roblox just introduced a suite of creator tools headlined by 4D Objects, generative AI that creates fully functional, drivable vehicles and interactive items from text prompts. The platform is also rolling out real-time voice translation and MCP support for its AI assistant, making game creation and global play remarkably seamless.
Snapchat just launched Imagine Lens, its first AI Lens powered by open text prompts. Instead of being locked into rigid preset filters, users can type whatever prompt they want to create or remix Snaps. It runs on a mix of Snap's internal and third-party models, but for now, it's exclusive to Platinum and Lens+ subscribers.
Krea AI just introduced Realtime Video, a model that generates frames faster than playback speed. Creators can sketch on a canvas, stream their webcam, or share their screen to direct temporally consistent video in real time. It turns sluggish video generation into an interactive, game-like creative tool.
PixVerse just launched its new V5 video generation model alongside an Agent feature, crossing 100M global users. The update improves motion consistency and visual clarity, rendering 360p clips in 5 seconds and 1080p in about a minute. The platform is offering free access during a launch event.
Google just shared an official playbook for squeezing the most out of Gemini's upgraded image tools. The guide breaks down how to maintain character consistency across shots, make precise local edits through conversational tweaks, and blend multiple images seamlessly. Google notes the model still struggles with typography and rigid aspect ratios, but iterative prompting is visibly improving.
HeyGen just rolled out Avatar IV, powering its Digital Twin with hyper-realistic gestures, natural head-to-toe body movements, and voice delivery tailored to each user's speaking style. Creators and executives can now produce personalized video content from scripts without stepping in front of a camera. The update is now live on HeyGen.
Google just integrated a new DeepMind image editing model into the Gemini app that finally keeps character likeness consistent across edits. You can now swap outfits, place yourself anywhere, and blend multiple photos together without your face or pet morphing into someone else. All generated images include invisible SynthID watermarks.
Adobe just integrated Google’s new Gemini 2.5 Flash image model directly into Firefly and Adobe Express. Creators can now tap Google's visuals across Text to Image and Firefly Boards, with paid subscribers getting unlimited generations through September 1. It cements Adobe’s strategy of turning Firefly into a multi-model creative hub while promising not to train on user data.
Researchers just introduced Wan-S2V, an audio-driven AI model that transforms a single image and audio track into synchronized, cinematic video. It handles expressive facial movements, full-body motion, and camera work, outperforming rival models across key benchmarks like video quality and identity consistency.
Sync Labs just launched Lipsync-2-Pro, a new video model designed to seamlessly alter what anyone says in any clip. It handles high-resolution video while keeping subtle details intact, from freckles to full beards. Why it matters: dubbing and re-recording clips will look a lot less like a blurry CGI filter.
Higgsfield AI just added the open-source WAN 2.2 model to its platform, supporting both video and image generation. It comes loaded with over 30 viral presets for one-click rendering, aiming to make fast video creation accessible without complex prompting.
Runway just launched its Game Worlds Beta, taking a major step toward letting users explore any character, story, or simulated world in real time. Beyond generating video pixels on the fly, the team is building novel mechanics and interfaces where user choices actively shape how simulations unfold.
