Do you store my generated audio?
No. Generated files are handed to your browser and cached on your own device. Once you leave or clear your browser data, they are gone — so download anything you want to keep, right away.
Is there a character limit?
Yes. Each generation has a maximum script length, shown live under the editor as you type. The limit keeps the service fast and fair for everyone sharing it.
Why can I only generate a few times per minute?
Speech synthesis is expensive. Per-minute, per-hour and per-day limits stop a single visitor from slowing the site down for everybody else. If you hit a limit, the message tells you exactly how long to wait.
Which voice should I pick?
Start with the most-used voices — they are at the top of the library by default. Filter by language, then use the preview button to audition before you commit. Favourite the ones you like; favourites are stored in your browser.
Can I use the audio commercially?
That depends on the individual voice and its licence. Check the usage terms for the voice you selected and read our Acceptable Use policy before publishing anything.
How do multi-speaker dialogues work?
In Dialogue Studio, assign a voice to each speaker, then tag each line in your script with the matching speaker marker. The platform creates the whole scene together so the timing feels natural.
My audio sounds robotic or rushed. What can I change?
Lower the speed slightly, raise expressiveness, and add stage directions in square brackets — for example [speaking calmly] or [with emphasis]. Small punctuation changes make a surprisingly large difference too.
Something is broken. What now?
Send us the details through the contact page: which page you were on, what you clicked, and what you expected to happen. Screenshots help.