When you press 'Generate' on the website, you will be deducted credits since the audio needs to be generated in order for you to hear it. This includes if you change the text and then regenerate, even in Projects or the Dubbing Studio.
We do permit two free regenerations in Speech Synthesis via the website in the following circumstances:
- The prompt (for text-to-speech) or file (for speech-to-speech), 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 this is the case, 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 in Projects, or Speech Synthesis via the API.
When using Projects, you can regenerate only specific paragraphs you are unhappy with and do not need to regenerate the whole text. Furthermore, in the Dubbing Studio, you do get some free credits when creating a dubbing project that you can use to regenerate some of the clips. But once these credits are exhausted, you will once again be deducted credits from your monthly quota.