Creating Text-to-Speech Audio via Asset Manager
Create text-to-speech in the production Create panel or from the Audio area in Asset Manager.
Creating Text-to-Speech Audio
Create text-to-speech in the production Create panel or from the Audio area in Asset Manager.
What you need first
Before you can generate speech from text, you need at least one saved voice.
If you do not have one yet:
- Open Asset Manager
- Go to Voices
- Click Create Voice
- Design and save a voice first
Production Create panel
When working in production, open the Create panel and choose the Speech tab. It has two fields:
- Dialogue: the exact words to generate
- Performance Direction: delivery guidance such as pacing, emphasis, energy, or pauses
Choose a saved voice, fill in the fields, then select Generate. Existing audio is not changed automatically; generating creates a new result for review.
Asset Manager workflow
- Open your project
- Open Asset Manager
- Go to the story's Audio folder
- Click Create Audio
- Choose Text to Speech
- Choose the saved voice and model
- Enter the text you want spoken
- Generate the audio
What happens after generation
The generated speech is saved back into the story as a reusable audio asset. You can then place it on the timeline, review it, or use it in a larger voice workflow.
Changing existing generated speech
To change wording or performance direction, generate a new speech result and replace or review the clip you want to use. Do not promise an in-place rewrite of an already generated audio asset unless that control is visible in the current workflow.