New models and features in AI image, video, voice and music generation, from Midjourney, Sora, Veo, Suno and more.
Higgsfield AI just introduced Higgsfield Speak, a new tool built to create motion-driven talking videos quickly. Users pick a style, select an avatar, and type in a script, while the platform automatically generates cinematic motion, voiceover, and facial emotion.
HeyGen just rolled out a major update to Avatar IV, adding script-driven dynamic gestures and hyper-real micro-expressions to its digital avatars. Users can now direct body movements directly via prompts in 1080p clips up to 60 seconds long. The feature is already available across all HeyGen accounts.
Luma AI just launched Modify Video, a video-to-video editing tool inside Dream Machine: Ray 2 that reimagines backgrounds, lighting, and characters while locking down original motion, facial expressions, and camera paths. In blind evaluations, Luma claims it consistently beats Runway V2V on temporal consistency and motion retention. It is a huge shortcut for creators who want rapid iterations without reshooting from scratch.
Runway just partnered with AMC Networks, the studio behind Breaking Bad and The Walking Dead, to integrate its AI tools into marketing and TV development. AMC plans to use Runway's models for promotional campaigns, VFX ideation, and accelerating pre-visualization during series creation. Why it matters: Entertainment powerhouses are actively embedding generative video tools straight into their core production pipelines.
Suno just rolled out a major upgrade to its Song Editor, giving creators granular control right from the waveform. You can now reorder and rewrite tracks section by section, split audio into 12 clean stems, upload songs up to 8 minutes long, and fine-tune output vibes using creative sliders.
ManusAI just launched its new video generation feature, turning single text prompts into fully structured, multi-scene video stories in minutes. The tool automatically plans scenes, crafts visuals, and animates the story. It is currently available in early access for Basic, Plus, and Pro subscribers, with wider access coming soon.
Microsoft just launched Bing Video Creator, a free text-to-video generator powered by OpenAI's Sora. Available now in the Bing mobile app worldwide (excluding China and Russia), it turns text prompts into 5-second vertical clips with 10 initial fast-generation credits. Why it matters: Everyday users can now test Sora's video capabilities without paying for a subscription.
Captions just rolled out Mirage Studio, powered by its proprietary omni-modal foundation model. Creators can upload an audio track, describe a scene, or drop in a reference photo to generate lifelike actors that laugh, flinch, sing, and rap on cue. It's available now for anyone looking to pump out high-energy video content in minutes.
Google just launched its top-tier Google AI Ultra plan in the UK, bringing access to its Veo 3 video generator to 73 countries. Pro subscribers can now tap into Veo 3 straight from the Gemini mobile app with a 10-pack of trial video generations. To tackle deepfakes, Google is also stamping visible watermarks on all clips except those made by Ultra members inside Flow.
Black Forest Labs just rolled out FLUX.1 Kontext, a new suite of models that generate and edit images using text and visual references side-by-side. It handles local tweaks and character consistency without complex workflows, accompanied by an open-weight 12B dev model on the BFL Playground.
Odyssey just launched a public research preview of its real-time interactive video platform. Powered by world models running on NVIDIA H100s, it lets users directly influence streaming video via keystrokes or joystick moves with 40ms latency at 30 fps. The team admits it still feels like a glitchy dream, but envisions a future where all video is interactive.
Google just rolled out its Veo 3 AI video generator to 71 new countries alongside bigger quotas for paid tiers. Gemini Pro subscribers now get a 10-pack trial on the web, while Ultra members get daily refreshed caps. Over on the filmmaker platform Flow, Ultra users saw their monthly generations bumped from 83 to 125.
Google just launched Veo 3, a video generator that creates eight-second HD clips with synchronized audio and sound effects. When developers put it to the classic "Will Smith eating spaghetti" benchmark, the visual realism was stunning, but the soundtrack glitched—making soft pasta crunch like potato chips. Why it matters: syncing audio to generative video introduces a whole new layer of training data biases.
Meta is testing a feature in its Quest v77 update that automatically turns regular 2D Instagram photos into 3D using AI view synthesis. The model reconstructs flat images pixel by pixel to add depth, meaning creators won't need expensive 3D cameras. The rollout begins this week for select testers.
TikTok just launched AI Alive, its first image-to-video feature that turns static photos into animated clips directly inside TikTok Stories. Creators can animate sunsets or selfies with motion and ambient effects, while every creation undergoes safety screening and includes C2PA metadata alongside an AI label.
Higgsfield AI just launched Effects Mix, a new upgrade that lets creators stack multiple cinematic VFX presets directly into a single video shot. Users can combine presets like fire, crash zooms, and metal textures or pick pre-made combos at the prompt level. The feature is live for all users, with paid tiers starting at $9/month.
HeyGen just rolled out Avatar IV, an advanced avatar model that brings a single photo to life using only an audio track. Instead of basic lip-syncing, its diffusion engine analyzes tone and emotion to generate natural micro-expressions, pauses, and head tilts. The feature is now rolling out to all users.
Midjourney just launched Omni-Reference, a new feature built to drop specific characters, objects, and vehicles directly into generated scenes. It basically acts as a "put THIS in my image" command, giving creators tighter consistency control without endlessly rerolling prompts.
Higgsfield just introduced a new Start & End Frames feature that lets users upload both an opening and closing image to shape their video. Instead of guessing where the camera will wander, creators can now enforce purposeful motion and a clear visual trajectory between two key points.
Ideogram just rolled out a major update to Ideogram 3.0, boosting realism, style versatility, and prompt adherence. Creators can now use Magic Fill and Extend inside Ideogram Canvas to edit uploaded or generated images, and the 3.0 model is officially live on the developer API.
