Pixverse v5.5: Text-to-Video AI Generator

fal-ai/pixverse/v5.5/text-to-video

Generate high quality video clips from text and image prompts using PixVerse v5.5

Inference

Commercial use

Partner

Schema

LLMs

Playground API

Input

Prompt*

Generate Audio Switch

Generate Multi Clip Switch

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

Download

{
  "video": {
    "file_size": 5485412,
    "file_name": "output.mp4",
    "content_type": "video/mp4",
    "url": "https://storage.googleapis.com/falserverless/model_tests/video_models/output-4.mp4"
  }
}

For a 5s video in single-clip mode without audio, your request will cost $0.15 for 360p and 540p, $0.2 for 720p, and $0.4 for 1080p. Enabling audio adds $0.05, and multi-clip mode adds $0.10 (or $0.15 with audio). For 8-second videos, costs double; for 10-second videos, costs are 2.2x the 5-second base (1080p not supported for 10s). For $1 you can run this model with approximately 2 times.

Pixverse Text to Video

Input

Result

What would you like to do next?

Logs