UrgulQ: More control over voice-over regeneration, tone and timing?
I’m testing Voicina and really like it so far, but I’m missing more control over voice-over editing.
If I generate a language version, e.g. German, I don’t see an option to delete/reset it and generate it again from scratch. Is this planned?
Individual phrases can be regenerated, but can we get options to choose the tone, generate 2–3 alternatives and pick the best one? Sometimes a sentence sounds too excited compared to the rest.
Some phrases also sound unnaturally sped up, as if forced to fit a specific duration. Will it be possible to control their timing/speaking speed?
And will we be able to delete individual phrases or sentences from the translated voice-over timeline? Currently I don’t see any way to remove them.
Are these features on your roadmap?
Mojtaba_Voicina
Oct 28, 2026A: Thank you for the detailed feedback, Urgul. Here is where each point stands:
Deleting/resetting a language version and generating it again from scratch: we don’t have this yet.
Choosing the tone and generating 2–3 alternatives of a phrase: we don’t have this yet either.
Unnaturally fast phrases: the dubbing has to fit the timing of the original speech, so some sentences get sped up. We’ve worked a lot on controlling the rhythm and improved it with a complex algorithm, but the AI output still struggles with this, and there is room to improve.
Deleting individual phrases from the timeline: we don’t have this yet. Related to this, right now we dub the video immediately after translating it, so you can’t edit the translation first. We agree this is needed, and a review step before dubbing is something we want to add.
We can’t promise dates yet, but these are valuable ideas and we’ll review them with our team. Please also add them on our feedback board so others can vote: https://voicina.supahub.com/en/b/feedback