Picsart Generative AI-Hub icon

Picsart Generative AI-Hub

Generate and edit media with Picsart GenAI API: images, stickers, sound, video, and prompt-based image editing.

Actions7

Generate Video from Prompt

AI-generated

Summary

Generates a video from a text prompt using Picsart's GenAI API.

Inputs

  • Prompt (required) — Text prompt describing the video to generate.
  • Width — Desired width in pixels (64-1024). Actual output is matched to the closest supported aspect ratio.
  • Height — Desired height in pixels (64-1024). Actual output is matched to the closest supported aspect ratio.
  • Quality — Video output quality tier (480p, 720p, 1080p).
  • Audio — Whether to include audio. Some models always include sound regardless of this setting.
  • Video Length (Seconds) — Desired video length in seconds (1-20). Mapped to the closest supported duration for the selected model.
  • Model — AI model for text-to-video (default: Veo 3.1 Fast). Resolution and audio behavior vary by model.

Output shape

One output item per input item containing a binary video file and metadata.

Returns a binary MP4 file with a JSON data object including the prompt, dimensions, quality, audio flag, length, model used, inference ID, and video URL.

Examples

Example 1: Generate a 3-second 720p video with audio from a simple prompt.

Prompt: 'A serene sunset over a calm ocean', Width: 1024, Height: 1024, Quality: '720p', Audio: true, Video Length: 3

Example 2: Create a short video using a specific model (e.g., Kling v3).

Prompt: 'A futuristic city at night', Width: 768, Height: 768, Model: 'urn:air:kling:model:kling:kling-v3-text-to-video@1'

Links

Discussion