ElevenLabs debuts unified beta for image and video generation with audio tools

ElevenLabs has released a beta version of Image and Video, combining visual and audio generation in a single workflow alongside its wide range of AI voice generation models. Users can now create images and videos inside the ElevenLabs Creative Platform using models such as Google Veo, Sora, KLING AI, Wan, Seedance, Nanobanana, Flux Kontext, GPT Image, and Seedream. Still images can serve as storyboards or thumbnails, and video creation supports model selection, refinement, clip composition, and quality improvements.

The platform also offers upscaling for images and videos and allows adding lipsync and narration with ElevenLabs voice models. Projects can be exported to Studio for further editing, where users can add voiceovers, use custom voice clones, create background music, layer sound effects, adjust timing, and refine narration on a single timeline.

These features aim to support creators, filmmakers, marketers, educators, and content teams looking for a unified place to produce multimodal content, with ElevenLabs positioning the beta as a move toward integrated visual and audio editing.