The Visla API now supports additional video creation methods, including generating videos from visual media, ideas, and speech.

Added

Added three new video creation endpoints to expand the supported video generation workflows in the Visla API.

Previously, developers could create videos from:

documents (ppt & pdf)
URLs / webpages
scripts

The API now also supports:

visual resources
speech
ideas

New endpoints

Create video from visual resources

POST /openapi/v1/project/visual-to-video

Creates a video project from images, videos, and optional text overlay.

Create video from speech

POST /openapi/v1/project/speech-to-video

Creates a video project from an audio or video file.

Create video from idea

POST /openapi/v1/project/idea-to-video

Creates a video project based on the provided idea.

Notes

These additions expand Visla’s video creation capabilities beyond the previously available document, URL, and script-based workflows, making it easier to generate videos from visual assets, spoken content, and early-stage concepts.

Changelog

Expanded Video Creation Capabilities

Visla Agent Skills