V4 Expressive Avatars

Create expressive videos where avatars can express different emotions through sentiments. Each sentiment represents a unique emotional state (like Professional, Empathetic, Excited, Friendly, Frustrated, etc.) and comes with its own voice configuration.

Create a video

Send a POST request with an avatar ID, sentiment ID, and the text you want the avatar to speak.

curl -X POST "https://api.d-id.com/expressives" \
  -H "Authorization: Basic <YOUR KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "avatar_id": "public_amber_casual@avt_PfMblk",
    "sentiment_id": "snt_aBC123ABc",
    "script": {
      "type": "text",
      "input": "Hello! Welcome to our platform. I am excited to show you around and help you get started."
    }
  }'

{
  "id": "exp_abC123",
  "object": "expressive",
  "status": "created",
  "created_at": "2020-09-03T13:56:54.995"
}

Save the id from the response — you'll need it to check the status and retrieve the video.

Call GET /expressives/avatars to see available avatars and their sentiments. Each sentiment automatically uses its configured voice for natural, expressive delivery.

Check the video status

Poll the GET endpoint until the status changes to done. Video generation typically takes 1-5 minutes depending on video length.

curl -X GET "https://api.d-id.com/expressives/exp_52907745-7672-470e-a803-a2f8feb52944" \
  -H "Authorization: Basic <YOUR KEY>"

{
  "id": "exp_abC123",
  "status": "done",
  "avatar_id": "public_amber_casual@avt_PfMblk",
  "sentiment_id": "snt_aBC123ABc",
  "result_url": "https://result.d-id.com/.../video.mp4",
  "duration": 4.5
}

Poll until status is done. Video generation typically takes 1-5 minutes depending on video length.

Get your video

Once the status is done, the result_url field contains a direct link to your expressive video. The avatar will display the selected sentiment throughout the video with appropriate facial expressions and animations.

curl -O "https://result.d-id.com/.../video.mp4"

The video uses the sentiment's configured voice, ensuring the voice tone matches the emotional expression of the avatar.