Discussions

Hi i am testing with the free trail to generate portraits with my own .wav sound for lipsync but the sound comes out very compressed once generated, is their a workaround this issue with the scale plan to have a clean sound?

I am using the you APIs to clone the voice. I noticed that there is an limit to the audios you can clone. If I purchase your Enterprise Plan can this limit be customised according to the need.

Microsoft voices have speed control, normally set by call to SSML, typically 1.0 = 100%. does your API have a config have a setting to set speed. if so, can you show the code for this?

كيف يمكن ان يتحول الى سطح المكتب

Good evening, I am organizing an exhibition about the Bicentennial and we want to make historical figures speak, such as José de San Martín and Simón Bolívar, I was trying before buying a plan, but a message appears, saying that it is not possible to make videos with these characters.
Is this prohibition maintained in the payment plans?

FYI..

I encountered this error when loading a video generated using the Talk Standard API on the D-ID API

Hello D-ID, I have some questions about your AI...

Is it possible to design an agent that support patient language towards API

How to generate a transparent talking head video?