HeyGen's AI video model from 1 cent per second

HeyGen has launched its new AI model, Video 1.0, enabling users to generate videos with sound based on text or images. With an introductory price starting at $0.01 per second, the company targets organizations that want to produce videos frequently at a lower cost. This makes the model particularly attractive to companies looking for cost-effective solutions for video production.

Video 1.0 is directly accessible via the HeyGen API, allowing developers to integrate the model into their own applications. Additionally, the model can be used through platforms like OpenRouter, Runware, and ComfyUI. This versatility provides companies the opportunity to apply the model in various environments, increasing accessibility and user-friendliness.

With HeyGen Video 1.0, users can create a video in three ways: by describing a scene, using an image as the first frame, or by uploading their own reference images. The model generates image and sound simultaneously, ensuring that each clip comes with audio, including spoken text, ambient sounds, and sound effects. This streamlines the process, as users do not need to work separately on each element.

For Dutch companies, especially marketing teams, this model offers exciting opportunities through the combination of image, sound, and low entry costs. It allows them to experiment with various scenes for product videos before arriving at a final version. However, it is essential to consider what the final costs for a usable clip are, especially if many iterations and edits are required. It may be beneficial to test with their own product images to assess effectiveness and suitability for their specific needs.

Read the full article from AI Insider.