Regenerations

How you can correct issues with your generations

Free Regenerations (Speech Synthesis)

If you’re using Speech Synthesis via the website, you can regenerate your audio twice for free in the following circumstances:

  • The prompt (for Text to Speech) or file (for Voice Changer), voice and model remain the same. You can change the voice setting sliders.
  • The first generation was made less than two hours ago.
  • You haven’t refreshed the page since generating the original audio.

If free regenerations are available, you will see “Regenerate speech”, and the number of free regenerations remaining will be displayed if you hover over the “Regenerate speech” button:

Once your free regenerations have been used, the button will return to “Generate speech”, and the number of credits that will be used for the generation will be displayed:

Free regenerations are only available in Speech Synthesis via the website. They are not available via the API.

Free Regenerations (Projects)

In Projects, provided you don’t change the text, you can regenerate a selected paragraph or section of text twice for free.

If free regenerations are available for the selected paragraph or text, you will see “Regenerate”. If you hover over the “Regenerate” button, the number of free regenerations remaining will be displayed:

Once your free regenerations have been used, the button will return to “Generate”, and you will be charged for subsequent generations.

Auto-Regenerate (Projects)

When you have Auto-Regenerate enabled for your project, we will automatically check the output for any mispronunciations or unwanted audio artefacts. If we detect any, we will automatically regenerate the audio up to twice, at no extra cost.

This feature will increase the processing time, and needs to be enabled.

You can either enable it in as an option in the Convert dialog window, if you’re converting your project or chapter in one step, or in Project settings, which will impact individual paragraph generation.

Feedback

To help us improve our error detection, you can flag sub-par generations. To do this, select the paragraph you want to flag, then use the speech bubble button to report the generation.