Introducing Studio Agent

Studio Agent, a conversational AI co-editing tool, has been introduced to the Studio timeline within ElevenLabs' ElevenCreative. Through a chat interface, users can structure a video, select voices, and place assets on the timeline.

Studio Agent drafts a first cut based on the user's request. Considering the video's length, tone, structure, and transitions, it automatically handles clip placement, voiceover generation, and sound effect syncing. Users can switch to manual editing at any time, and can choose between Create mode, which grants the agent editing authority, and Plan mode, which only provides advice.

The Frame-level audio placement feature in particular is a key highlight. When a user gives a natural-language command like "add a sound effect when the logo appears," the AI analyzes the video content and places the audio at the exact visual timestamp.

Key features include the following:

• Extensive voice library: Support for 32 languages and over 10,000 voices.
• Efficient workflow: Voice audio can be edited simply by revising the script, eliminating the need for re-recording.
• Use of existing assets: Users can start editing by dragging in their own files or importing existing generations.