ElevenLabs has introduced Image & Video, a beta feature that integrates visual generation models into its platform. Users can create images and videos, add voices and music, and export final content in a single workflow.
ElevenLabs has announced the launch of Image & Video in beta version, a new feature that incorporates visual generation models into its audio-specialized platform. The tool allows users to create visual and audio content from the same work environment.
The platform integrates several models for image creation, including Nanobanana, Flux Kontext, GPT Image, and Seedream. These images can be used as storyboards, thumbnails, or source material for video projects.
For video generation, ElevenLabs has incorporated models such as Veo, Sora, Kling, Wan, and Seedance. Users can refine results, compose multiple clips to create narratives, and apply quality improvements through upscaling functions. The platform also allows adding lip sync to generated videos using ElevenLabs voices.
Once visual elements are created, users can export them to Studio, the ElevenLabs editing environment. In Studio, it is possible to add narrations with voices from the library or custom clones, compose specific background music, and add sound effects. The system includes a unified timeline to adjust synchronization and refine narration before exporting final content.
The company has oriented this feature toward content creators, marketing teams, and educational producers. According to ElevenLabs, the tool allows creating product videos, social media content, and educational materials from ideation to final export.
This launch represents ElevenLabs' expansion beyond its audio specialization, integrating visual generation, editing, and sound production capabilities into a single platform. The Image & Video feature is available on the ElevenLabs Creative platform in its beta phase.
Explore the most advanced text to speech and voice cloning software ever. Create lifelike voiceovers for your content or use our AI voice generator as an easy-to-use text ...
05/03/2026
OpenAI has released GPT-5.4, a model that combines advanced reasoning, coding and computer control into a single tool designed for complex ...
02/03/2026
Anthropic rejects removing two restrictions on its AI's use by the military, in a conflict that led Trump to order its removal from all federal ...
25/02/2026
Perplexity introduces Computer, an AI agent capable of creating and executing complete workflows for hours or months, autonomously coordinating ...
23/02/2026
Anthropic has identified large-scale campaigns by DeepSeek, Moonshot and MiniMax to fraudulently extract capabilities from its Claude model and use ...