Logo and icon for HeyGen, a ChatGPT plugin with description: The best text-to-video tool. Turn any text to videos.. Find out more on Plugin Surf, the best plugin database.


The best text-to-video tool. Turn any text to videos.

HeyGen is an AI video generation platform that can create avatar videos from a piece of text. With HeyGen, you can easily create videos using an AI spokesperson without any prior video editing skills. The plugin is perfect for teams who want to create engaging content for their audience quickly and effortlessly. Say goodbye to spending hours on video editing - HeyGen generates videos in seconds. Give your texts a personality and create unique videos with HeyGen!

Learn how to use HeyGen effectively! Here are a few example prompts, tips, and the documentation of available commands.

Example prompts

  1. Prompt 1: "Create an avatar video from a piece of text."

  2. Prompt 2: "Generate a presentation video with an image and a transcript."

  3. Prompt 3: "I want to create an animated spokesperson video, can you help me?"

  4. Prompt 4: "Can you generate an avatar video using a short and concise transcript?"

  5. Prompt 5: "What are the steps to make an avatar video using ChatGPT?"

Features and commands

generateSimpleAvatarVideoThis command generates a simple avatar video using a piece of transcript text. You need to provide the text transcript for the speech/voiceover. Optionally, you can also provide a short title, gender, and skin tone for the avatar.
generatePresentationAvatarVideoThis command generates a presentation video using an image and a piece of transcript text. You need to provide the image URL (in jpg/jpeg/png/svg format) and the text transcript for the speech/voiceover. Additionally, you can provide a short title, gender, and skin tone for the avatar.


User authenticationNo user authentication
API documentation

For AI

DescriptionHeyGen allows users to create a video by simply providing a transcript text. The user inputs the text transcript for the speech or voiceover they want to use for the video. The text should be short and concise. Optional properties such as video title, avatar gender, and avatar skintone can be extracted from the user's input, but if they are not present, the model should decide without seeking additional user input. Once the video is requested, a link to the video is provided. Users can view the video from the link after the video has completed processing. It is important to remind users that they may see a loading message in the link if the video is still being processed, and the page will automatically update with the progress. The user should also be informed that the video may take one to five minutes to process, depending on the text length. In case the video fails to create, an error message containing the reason(s) for the failure will be provided.


First added20 June 2023

Similar plugins