Adobe has unveiled new AI innovations across its video and audio applications.

The new beta releases across Premiere Pro, After Effects and Frame.io have new AI-powered features to automate “time-intensive” tasks.

Premiere Pro adds AI-powered features including Enhance Speech for quicker dialogue cleanup, filler word detection and removal in Text-Based Editing, and improved Auto Tone Mapping for more consistent colour output. The timeline is now “five times faster”.

Enhance Speech uses AI to remove background noise and improve the quality of poorly recorded dialogue. The new Audio Category Tagging uses AI to determine which clips contain dialogue, which contain music, and which are sound effects or ambient noise. When each audio clip is selected, the most relevant tools are automatically displayed.

Premiere Pro introduced Text-Based Editing earlier this year. Text-Based Editing now includes filler word detection to automatically identify “ums” and “uhs” in dialogue. Users can quickly remove those filler words, pauses or any other unwanted dialogue in one step using bulk delete.

After Effects has new AI rotoscoping capabilities to streamline After Effects workflows by removing objects faster and more accurately.

Hard-to-isolate objects such as overlapping limbs, hair, and transparencies are separated from their background with a new AI model in the Roto Brush tool. With this addition, editors, motion designers, and VFX artists can “shave off hours of tedious rotoscoping work, enabling you to focus on the more creative aspects of your projects.”