D-ID | AI Agent Tools

d-id.com

•

API Key

About D-ID

D-ID is a generative AI platform that allows businesses to create high-quality videos featuring digital avatars. Users can turn text into video presentations, customize avatars, and use extensive voice and language options. The platform is ideal for marketing, training, and storytelling, offering cost-effective video production and scalability. It supports video creation in over 120 languages, enabling businesses to connect with global audiences effectively. By leveraging D-ID, companies can enhance their content with realistic avatars, reducing production costs and increasing engagement.

AI Agent Use Cases

• AI agents can utilize D-ID to automate the creation of personalized video content for customer engagement, such as generating multilingual support videos or interactive product demos. Agents can also leverage D-ID's API to integrate AI avatars into chatbots and live support systems, enhancing customer interaction with real-time video responses. Additionally, AI agents can automate the process of updating video content by using D-ID's generative AI tools to reflect changes in branding or messaging across all video assets.

Available Actions

These are the specific actions that AI agents can perform with this tool

Create Clip

10 inputs

Creates a new video clip using the D-ID service.

Inputs

presenter_id

An identifier for the presenter of the clip. If not provided, defaults to jack-Pt27VkP3hW.

script

Specifies the script type and content for the video, including provider and input.

config

Advanced configuration options for the clip.

presenter_config

Advanced configuration options for the presenter of the clip.

background

Background color configuration for the clip.

user_data

Custom non-sensitive data included in clip response and webhook.

name

The name of the clip.

webhook

A URL to send the payload with animation details. If empty, the webhook won't be triggered.

result_url

URL for the clip video, defaults to the service's storage if not provided.

persist

Indicates if the video should be stored permanently without TTL.

Create Video Stream

5 inputs

Create a video stream using a specified agent and stream ID.

Inputs

agentId

The ID of the agent for whom the stream is being created.

streamId

The identifier for the video stream being created.

script

The script object containing type, provider, and ssml settings.

config

Configuration settings for the video stream, including fluency and audio padding.

audio_optimization

Specifies the level of audio optimization required.

Delete Video

2 inputs

Delete a specific video by its agent and stream identifiers

Inputs

agentId

Agent Id required to identify the video

streamId

The stream identifier associated with the video

Generate Digital Human Video

2 inputs

Generate a video of a talking digital human from an image and audio file.

Inputs

imagePath

The path to the image file that will be used to create the base appearance of the digital human.

audioPath

The path to the audio file that contains the speech the digital human will speak in the video.

Get Agents List

Retrieve a list of all Agents available in the user's account

Get HQ Presenters List

2 inputs

Retrieve a list of HQ Presenters available for use.

Inputs

limit

The number of presenters to return; defaults to 100.

token

The pagination token from the previous response.

Get Video

3 inputs

Retrieve a video using D-ID's API given an image and text or audio input.

Inputs

image

The input image that will be used to generate the video of the digital human.

text

The text that the digital human will speak in the generated video.

audio

An alternative to text input; audio data that the digital human will use for generating the video.

List Consents

Retrieve a list of consent details from the API.

List Videos

3 inputs

List all available videos in the D-ID platform.

Inputs

apiKey

API key used for authenticating requests to the D-ID API.

page

The page number to retrieve, for paginated results.

pageSize

The number of results per page.

About D-ID

AI Agent Use Cases

Available Actions

These are the specific actions that AI agents can perform with this tool

Create Clip

10 inputs

Creates a new video clip using the D-ID service.

Inputs

presenter_id

An identifier for the presenter of the clip. If not provided, defaults to jack-Pt27VkP3hW.

script

Specifies the script type and content for the video, including provider and input.

config

Advanced configuration options for the clip.

presenter_config

Advanced configuration options for the presenter of the clip.

background

Background color configuration for the clip.

user_data

Custom non-sensitive data included in clip response and webhook.

name

The name of the clip.

webhook

A URL to send the payload with animation details. If empty, the webhook won't be triggered.

result_url

URL for the clip video, defaults to the service's storage if not provided.

persist

Indicates if the video should be stored permanently without TTL.

Create Video Stream

5 inputs

Create a video stream using a specified agent and stream ID.

Inputs

agentId

The ID of the agent for whom the stream is being created.

streamId

The identifier for the video stream being created.

script

The script object containing type, provider, and ssml settings.

config

Configuration settings for the video stream, including fluency and audio padding.

audio_optimization

Specifies the level of audio optimization required.

Delete Video

2 inputs

Delete a specific video by its agent and stream identifiers

Inputs

agentId

Agent Id required to identify the video

streamId

The stream identifier associated with the video

Generate Digital Human Video

2 inputs

Generate a video of a talking digital human from an image and audio file.

Inputs

imagePath

The path to the image file that will be used to create the base appearance of the digital human.

audioPath

The path to the audio file that contains the speech the digital human will speak in the video.

Get Agents List

Retrieve a list of all Agents available in the user's account

Get HQ Presenters List

2 inputs

Retrieve a list of HQ Presenters available for use.

Inputs

limit

The number of presenters to return; defaults to 100.

token

The pagination token from the previous response.

Get Video

3 inputs

Retrieve a video using D-ID's API given an image and text or audio input.

Inputs

image

The input image that will be used to generate the video of the digital human.

text

The text that the digital human will speak in the generated video.

audio

An alternative to text input; audio data that the digital human will use for generating the video.

List Consents

Retrieve a list of consent details from the API.

List Videos

3 inputs

List all available videos in the D-ID platform.

Inputs

apiKey

API key used for authenticating requests to the D-ID API.

page

The page number to retrieve, for paginated results.

pageSize

The number of results per page.