Skip to main content
Glass creative studio tools for art, film, music and narration
AI Studio is Aura’s creative production workspace. Its five main tabs are Imagine, Music, Speech, Transcribe and Media. Use them together to move from an idea to artwork, moving pictures, a soundtrack, narration and finished files.

Watch AI Studio

Every part of the workspace

Explore the guides

Create and edit images

References, format choices and focused masked edits.

Create videos

Short clips, compatible media references and model-specific controls.

Lip sync

A portrait plus recorded or generated speech.

Music and video scoring

Songs, lyrics, soundtracks and finetunes.

Edit songs

Target sections, insert precisely and batch saved edits.

Speech and voices

Choose a voice, shape delivery and export narration.

Transcribe

Recordings to text, with speaker and event options.

Media and downloads

Find, preview, reuse and manage finished work.
Glass library containing creative images, video and audio

Combine the tools

1

Create the visual

Make an image in Imagine and use it as a supported video reference, or prepare a portrait for Lip sync.
2

Add voice or music

Create narration in Speech, compose a track in Music, or score an uploaded video with Music’s Video mode.
3

Refine the result

Remix visual work or target music sections. Use Saved Edits when several song changes belong together.
4

Review and keep the files

Play and inspect the finished output, then download it or return through the workspace’s history and Media library.

Access, credits and privacy

AI Studio generation/editing controls require Pro or Elite. Free and Essential members can explore preview-only controls; browsing does not unlock generation. Free members can separately generate 2 images per rolling hour in chat. Choose a model and supported settings, then read the displayed credit estimate. Image/video models, duration, resolution, variations, narration length, music generation, edits and training can affect usage. Do not assume all operations have one flat price. Imagine and Music display Non-ZDR notices. Speech and Transcribe have their own privacy badges. A ZDR setting in chat does not turn a different creative service into a ZDR service. Avoid sensitive prompts and private references in Non-ZDR operations. See plans and privacy.

Common questions

No. Imagine includes Image, Video and Lip sync; its settings depend on the selected mode and model.
Yes. The song editor supports section targeting, precise insertion, extending and restyling, plus Saved Edits applied together.
No. Speech turns text into audio; Transcribe turns an uploaded recording into text.
Aura Agents has its own top-level docs tab. It handles recurring or event-driven work, not Studio production settings.