Generate Speech From Another Audio Using AI
This guide provides a simple and effective approach to transforming existing audio into new speech using AI. It walks you through each step — from selecting a voice to generating and previewing the final output.
1. Navigate to your storyboard page. Click on "Speech" button.
2. Click the square icon in the bottom right corner to open the advanced menu.
3. Select the voice you want to use for speech generation.
4. Click "Speech to Speech" tab to switch to "Speech to Speech" mode.
5. Click "Browse Files" and select your input audio file from your device or computer.
6. Wait for the audio file to upload.
7. You can preview the input audio by clicking play.
8. Click "Generate Speech" to start generating your speech.
9. Once your speech is generated, click the play button in the audio player at the bottom to preview it.
10. The generated speech is automatically added to your storyboard. Click "X" to close the modal once you're done.
11. The input audio will be visible in your shot here.
12. The generated speech will be visible at the bottom in the highlighted area.
