Discussions

Ask a Question
ANSWERED

How can three people in one picture can speak according to the given text

I have a picture with three people, and I am using the Thunder Client SDK in VSCode. However, when I insert an image featuring three people and assign names and text to each person, the output only displays a video with one person, and all the text is spoken by that one person. I want the generated video to depict all three people speaking when it is their turn in the debate on a topic. Each person presents their point of view. If anyone has code or guidelines, it would be greatly appreciated.

ANSWERED

internal server error

POST https://api.d-id.com/talks is returning an in ternal server error

ANSWERED

Uzsākt darbu

Kur ir jāievieto API atslēga

ANSWERED

Error when using an Azure Storage Account with SAS as result_url

I'm migrating an app that uploads the Talks result in an S3 to upload the result on an Azure Storage Account. It works perfectly with S3, but when using an Azure SAS URL I am getting the following error:

ANSWERED

Issue with API: Receiving Internal Server Error with ElevenLabs Provider

Here's the translation of your message into English:

ANSWERED

The face shape change too much when the photo speak

I tried your AI video, when the photo speak, the face shape change too much.

ANSWERED

How to access S3 result_url video file?

Hello,

ANSWERED
ANSWERED

Interactive Ai Agent that uses GPT4 for responses

How can I create an "Agent" that I can talk with in real time and have conversations about PDFs of Texts I upload as a Knowledge Base?

ANSWERED

Why is silent Video generation now not working ??!!!

I have generated a number of videos with the clock / timer icon to make a silent Video (as before) but now the video tells me I have a 7 second video which then generates just a 0 second video which I can not use ??