ElevenLabs
Studio 4.0 lets ElevenLabs users generate video, images, voice, music and sound effects without leaving their project. Every model in ElevenCreative is now available inside the editor.
You can describe a shot, generate it, refine the result and place it on the timeline. The same project can hold the voice track, music, sound effects and captions before export.
The launch also brings a rebuilt timeline for multi-scene, multi-track work and a Studio Agent that can turn a script into a first draft. ElevenLabs is positioning the editor for in-house creative teams, agencies and marketing teams producing finished videos at volume.
The details come from the Studio 4.0 LinkedIn announcement.
Studio 4.0 brings five media types into each project
The editor now covers the main components of a finished video. Builders can generate the visuals, narration, soundtrack and individual sound effects inside the same project, then add captions and export the result.
This brings ElevenCreative’s models directly into the production workflow. Rather than generating an asset and treating the editor as a separate destination, users can describe the shot they need and continue refining it where the final video is assembled.
Music is part of that combined workflow. ElevenLabs had already expanded its music product with Music v2.5 across every ElevenMusic plan. Studio 4.0 places music generation alongside the other media used in a video project.
| Production task | Studio 4.0 behaviour | Where it happens |
|---|---|---|
| Create visuals | Generate video and images from a description | Inside the project |
| Produce audio | Generate voice, music and sound effects | Inside the project |
| Refine a shot | Describe, generate and revise the required material | Inside the editor |
| Finish the video | Edit, caption and export the assembled work | In the same workspace |
The rebuilt timeline handles scenes, tracks and captions
Studio’s timeline has been rebuilt for projects containing multiple scenes and tracks. It now supports frame-level zoom and clip snapping, giving editors more control over the position of each asset.
Related clips can stay in sync when they are moved. That applies when an edit requires a section of the project to shift without separating material that belongs together.
Captions now behave like other clips on the timeline. Editors can select and edit them in place. If the transcription contains the wrong word, it can be corrected on the timeline rather than sent to a separate caption tool.
The combination supports a workflow in which generated material and manual edits share the same timeline:
- 1
Start with the script
give Studio Agent the source material for the video
- 2
Build the first draft
let the agent assemble an initial version
- 3
Refine the media
describe and revise the required shots, voice, music and effects
- 4
Edit the timeline
arrange scenes, snap clips and keep related material in sync
- 5
Fix the captions
correct mistranscribed words directly on the timeline
- 6
Export the project
produce the finished video from the same editor
Studio Agent drafts the project and hands back control
Studio Agent can build an initial video draft from a script. It does not require the agent to remain in charge of the whole editing process. The user can take control whenever they want and continue working directly in the editor.
That gives Studio 4.0 two working modes within one project. The agent can assemble the starting point, while the timeline provides frame-level controls for the subsequent edit. Generated video, images and audio can then be revised alongside captions and existing clips.
ElevenLabs says some of its largest enterprise customers already use Studio to combine voice and video. Studio 4.0 expands that setup to include generation for all five media types and an agent-led first draft.
Frequently asked questions
What is ElevenLabs Studio 4.0?
Studio 4.0 is an editor for generating and assembling video, images, voice, music, sound effects and captions in one project. It includes the ElevenCreative models, a rebuilt multi-track timeline and Studio Agent for creating a first draft from a script.
What can Studio 4.0 generate?
Studio 4.0 can generate video, images, voice, music and sound effects directly inside a project. Users can describe and refine shots before editing, captioning and exporting the finished video.
How does Studio 4.0 compare with the previous editing workflow?
The timeline has been rebuilt for multi-scene, multi-track projects with frame-level zoom, clip snapping and clips that remain in sync when moved. Captions can now be corrected directly on the timeline instead of in a separate tool.
Who is Studio 4.0 designed for?
ElevenLabs describes Studio 4.0 as a product for in-house creative teams, agencies and marketing teams. Its stated use case is producing finished video at volume.
Sources
4 checkedHow we cover tool news: Create With's tool desk drafts these reports with AI from the sources listed above and checks them against those sources before publishing.
Vercel
Airtable
Bubble
Netlify
Granola