Ask a Question

Generating documents for knowledge base real time.

I was able to create instructions that required the user to provide a code to get information on a proposal. The proposal information was provided in the AI instructions. I want to be able to do the following: - Continuously send proposal information for customers via one AI via an API - Customers can retrieve their own proposal via the AI after entering a code. - Remove the proposal information after a specified period of time to free up storage.

API Create clip stream for realtime endpoints raise Internal Server Error When i use ElevenLabs provider with my voice id

{'kind': 'UnknownError', 'description': 'Internal Server Error'}

when the user ask the avatar, and I give the answer as a text to the avatar to replay to the user?

can I give the response to the avatar to replay with it to the user instead of using the AI generator to generate the response?

how to use Api-Key.

Can I get a sample code that uses a simple api-key? Please.

Unexpected identifier 'assert'

Uncaught SyntaxError: Unexpected identifier 'assert streaming-client-api.js: 'use strict'; import DID_API from ./api.json assert { type: 'json'};

Clip persistence

Hi there, Once a clip is rendered, how long does it persist on your servers before it gets deleted? Thanks, Manu

Speech suppression

Hi, Just playing with the agent function there and it's very clever. I've built a Q&A and some of the answers have url's as replies. Is it possible to get the agent to not speak certain parts of the reply as it's reading out the whole url. Thanks.

Support of Persian or Farsi language in agent

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

I want to use within make the function

Hello, <br /> I want to use within make the function. However, I get an 401 error. API token has been created. I am a bit desperate meanwhile. The same token works within the development section of d-id.com perfectly. Can you help please? Best regards

How to control the size of the mouth opening and closing when making a picture talk.

Currently, the mouth movements in my voice-driven talking pictures are too exaggerated. Therefore, I would like to know how to control the size of the mouth opening and closing when making a picture talk. Can you help me,Thanks!