1. Get Started
PixVerse Platform Docs
  • Get Started
    • What Is PixVerse AI?
    • Model Capability Map
    • Billing and Usage
    • Quick Start
    • Contact Us
    • Privacy and Data Protection
  • API
    • Preparation
      • Start Here
      • Concurrency Rules
      • Query Task Status
      • Error Codes
      • FAQ
      • Webhook Callbacks
      • Upload Image
      • Upload Media (Video and Audio)
      • Verify Uploaded Audio
      • Get Effect Template List
      • Get TTS Speaker List
      • Get Restyle Effect List
      • Query Task Status
      • Get Account Balance
      • Usage Deduction Query
      • Create Custom Voice
      • Delete Custom Voice
    • Core Capabilities
      • Text-to-Video
      • Image-to-Video and Video Templates
      • First and Last Frame Video
      • Reference-to-Video (Fusion)
      • Multi-Transition Video
      • Video Extend
      • Image Template Generation
      • Get Image Generation Result
    • Solutions
      • Video Upscale
      • Video Restyle
      • Lipsync
      • Video Edit (Modify)
      • Image Avatar
      • Select Video Mask
      • Sound Effect
      • Subject Replacement (Swap)
      • Motion Control (Mimic)
      • One-click Real Estate Video
      • One-click VibeMV
  • Pricing
    • PixVerse API Pricing
  • Changelog
    • Changelog
  1. Get Started

What Is PixVerse AI?

The PixVerse API Platform provides AI video generation and editing capabilities for content creation, media production, entertainment, e-commerce, and advertising workflows.
Create and manage your API integration at https://platform.pixverse.ai.
For programmatic error handling, check ErrCode. Treat ErrMsg as a human-readable message whose wording or capitalization may vary.

Platform Highlights#

1.
Multiple generation workflows
Build Text-to-Video, Image-to-Video, First and Last Frame Video, Reference-to-Video, Video Extend, template-based effects, and specialized editing workflows.
2.
Controllable output
Supported endpoints expose controls such as prompts, aspect ratio, duration, resolution, seed, audio, and model-specific options. Available combinations vary by endpoint, model, and account.
3.
Reusable uploaded media
Upload images, videos, and audio once, then pass the returned img_id or media_id to compatible generation endpoints.
4.
Asynchronous task processing
Generation endpoints return a video_id. Poll Query Task Status or use a Webhook, and treat the task as complete only when status=1 and the output URL is accessible.
5.
Server-side integration
Unified authentication, media upload, task creation, status retrieval, and billing records support production integration with content tools and automated workflows.

Core Capabilities#

Text-to-Video#

Generate video from a text prompt describing the subject, action, setting, camera movement, and visual style.

Image-to-Video#

Animate an uploaded image while preserving the source subject and composition.

Video Templates#

Generate repeatable effects with a supported template_id. Use the live template list to check required inputs, supported specifications, and Credit consumption.

Reference-to-Video#

Generate a new video from supported image or video references. Input requirements and model availability are defined on the endpoint page.

Video Editing and Motion#

Extend, restyle, upscale, modify, or replace parts of an existing video, and drive a target image with reference motion where supported.

Audio, Speech, and Avatars#

Add sound effects, synchronize lip movement with uploaded audio or TTS, and create talking-avatar videos from a portrait and audio input.
Next
Model Capability Map