gen‑ai.news
← Back
Video

Adobe Unveils New Generative Media Tool in Premiere, Plus More AI-Powered Updates

Adobe Unveils New Generative Media Tool in Premiere, Plus More AI-Powered Updates

Adobe used IBC 2026 as the stage to announce a broad set of updates to Premiere Pro and After Effects, with the centerpiece being a new Generative Media Tool built directly into Premiere's editing timeline. Until now, much of Adobe's generative AI work has lived inside the Firefly web editor, so moving these capabilities into Premiere represents a meaningful shift in where and how editors can access them during their day-to-day work.

The Generative Media Tool lets editors describe what they need in text, and Premiere will produce context-aware video and audio clips that are editable and refineable without leaving the project. At launch, the tool supports multiple underlying models - editors can choose between Adobe Firefly and third-party options including Google Veo, Kling, Runway, and Luma. Specific functions include Generate Video, which fills timeline gaps using reference frames sampled from the surrounding edit to better match the visual tone of existing footage; Generate Sound Effects, which uses Adobe's audio model and can accept voice input to guide rhythm and timing; Generate Soundscape (beta), which analyzes up to 15 seconds of video and builds a layered ambient audio bed to match; and Generate Music (beta), which produces original, commercially licensed music with tempo and looping controls.

Beyond the generative tools, Adobe is also adding a set of audio processing upgrades. Enhance Audio extends the existing Enhance Speech feature with more granular noise reduction, giving editors independent control over dialogue, music, ambience, and sound effects within a single clip. Separate Crosstalk automatically splits overlapping speakers into distinct tracks, Dynamic Auto Ducking handles level balancing between dialogue and music without manual keyframes, and a new speed-change algorithm preserves pitch and timbre more naturally across a wider range of duration adjustments.

After Effects is also getting attention, with AI Assistants entering public beta inside AE to help accelerate composition work. On the color side, Adobe is introducing a new Color Mode with Style Modules - including Vignette and Midtones controls - aimed at building cinematic looks more efficiently. Taken together, the updates reflect Adobe's continued push to weave AI-assisted tools into the core editing environment rather than keeping them as separate or supplemental products.

Enjoy this story? Get the next one in your inbox.

Twice a week: the most important stories in generative image and video AI, distilled into a 2-minute read.

Free. Unsubscribe any time. No spam, ever.

Your next read

No image
Video

Runway’s WorldPrompt and the Engineering of Real-Time Worlds

Runway's WorldPrompt system powers its Gen World Models 2 (GWM 2), enabling real-time generation of video and audio through persistent context and timed actions. Rather than producing discrete clips, the model maintains a continuous understanding of an environment as it unfolds. The approach marks a notable shift in how world models can be steered interactively.

Gemini 3.8 Live with Live Avatar gives Google’s AI a face
Video

Gemini 3.8 Live with Live Avatar gives Google’s AI a face

Google has updated Gemini Live with an animated avatar that lip-syncs and displays facial expressions in real time during conversations. Called Live Avatar, the feature is currently limited to Gemini Enterprise customers and supports 97 languages without degrading video quality. It marks Google's latest step toward giving its AI assistant a visible, expressive presence.

No image
Video

Introducing Gemini 3.8 Live with Live Avatar

Google DeepMind has introduced Gemini 3.8 Live, an updated multimodal model paired with a new Live Avatar feature that generates an animated, talking on-screen presence during real-time conversations. The combination allows users to interact with a responsive visual agent rather than a purely voice-based interface. The release marks another step in Google's effort to make AI interactions feel more immediate and embodied.