Discussions

We have a custom-built chatbot that utilizes our internal knowledge base and cloned voices for responses. We're interested in using D-ID's avatar technology purely for the visual component—to generate a talking head that can lip-sync with our custom audio.

Is it possible to integrate your avatars in this way? Specifically, can your API or platform support the use of pre-generated voice (audio) while using only your avatar for video generation? We do not need the full TTS functionality—just the avatar animation synced with our audio.