XNews

[ElevenLabs Studio 3.0] Major Studio 3.0 Launch/Update

ElevenLabs Studio 3.0: a major product release that consolidates advanced AI audio models into a single editor and adds native video support. The update introduces expressive TTS voiceovers, integrated music generation (Eleven Music), sound effects, voice isolation and voice changing, automatic captioning, and a Speech Correction feature that regenerates corrected lines in a user's voice without re-recording. Studio 3.0 also adds a multiplayer commenting workflow and a one-timeline video/audio editing process that removes the need to export and re-import assets. The release is positioned to streamline audio-for-video production, improve post-recording fixes, and support collaborative review within the editor.

Key insights

Studio 3.0 centralizes advanced AI audio models in one editor

Studio 3.0 brings multiple AI audio capabilities—voiceovers, music, sound effects, voice isolation, and voice changing—into one editor so creators can produce, layer, and export audio without leaving the product.

Speech Correction enables edited lines to be regenerated in the original voice

When a clip with speech is added, Studio 3.0 transcribes the script into the editor; users can edit text and use Speech Correction to re-generate the corrected line in the same voice without re-recording.

Native video support and one-timeline workflow simplify audio-for-video production

Studio 3.0 accepts uploaded video files, generates context-aware music with Eleven Music, and allows full audio enhancement and export from a single timeline, removing the previous need to export and re-import assets into external video editors.

Multiplayer commenting provides time-stamped feedback directly in the timeline

Studio 3.0 introduces a multiplayer mode that lets teammates add time-stamped comments via shareable feedback URLs, intended to replace long feedback threads in external communication tools.

Source posts