Voice generation

Write a script, pick a voice model, and import the result straight into the open project.

The voice studio is a tab in the same workspace as the editor, so a generated narration track lands in the project you already have open.

The Voice Generation studio with a voice picker and a script composer — Pick a voice model, compose the script, generate, and import the finished audio as a project asset.

The flow

Connect a speech provider — ElevenLabs or OpenAI — in Settings → Providers
Choose a voice model in the studio's picker
Write or paste the script
Generate, and follow the job while it runs
Import the result; it becomes an asset in the open project, ready for a timeline track

Where results are written

Generated audio is written into the project folder alongside your other assets — see Projects and folders. Nothing is uploaded except the script text you asked to be spoken, sent to the provider you connected.

Boundaries

Voice generation requires a cloud provider; there is no local speech engine in this build. Providers listed without a real adapter stay unavailable rather than failing halfway through a job.