Wan V2.2 A14B
wan / 2-2-a14b-text-to-video-turbo

Wan 2.2 A14B Turbo API, an open-source generation of the Wan video model, is built with a Mixture-of-Experts (MoE) architecture and supports text-to-video (T2V), image-to-video (I2V) and speech-to-video(S2V). It delivers smooth clips at up to 720p with cinematic quality, stable motion, and consistent visual style for diverse creative and commercial use cases.

Model Type:
Pricing: wan v2.2-a14b turbo costs 16 credits per video second for 720p ($0.08), 8 credits per video second for 480p ($0.04) High-tier top-ups (+10% bonus) bring effective pricing down to ~$0.073 per second (720p) and ~$0.036 per video (480p).
Input

The text prompt to guide video generation.

0/5000

Resolution of the generated video (480p, 580p, or 720p). Default value: "720p"

Aspect ratio of the generated video (16:9 or 9:16). Default value: "16:9"

Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning.

Random seed for reproducibility. If None, a random seed is chosen.

Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'none'. Default value: "none"

A configurable parameter. Defaults to true in the Playground.

There is no guarantee that everything can be filtered out; if you are not satisfied with the results, you will need to make your own arrangements.
Output
output typevideo
Examples

Explore different use cases and parameter configurations

README

Complete guide to using Wan V2.2 A14B

Wan 2.2 Turbo API -T2V&I2V&S2V-A14B

ModelKey Feature
Text-to-Video Turbo (Wan 2.2 T2V A14B API)Transforms detailed text prompts into cinematic videos at 480p or 720p with Turbo acceleration for fast, high-quality clip generation.- Resolution: 480p or 720p, 16:9 or 9:16 - Turbo Acceleration: Fast video generation - Coherent Motion: Fluid, natural sequences - Consistent Style: Uniform visual aesthetics - Customizable Prompts: Tailored content and mood
Image-to-Video Turbo (Wan 2.2 I2V A14B API)Animates static images into smooth cinematic videos using a high-resolution image and descriptive prompt to guide motion and style.- Image Animation: Smooth transitions from static images - Prompt-Guided Motion: Precise camera control - Style Customization: Defined visual aesthetics - High Compatibility: Supports various image formats - Fast Processing: Quick rendering with Turbo
Speech-to-Video Turbo (Wan 2.2 S2V A14B API)Turns static images and audio clips into dynamic, expressive videos, ideal for storytelling, marketing, and education, with seamless Kie.ai integration.- Audio-Driven Animation: Syncs audio with visuals - Multi-Input Support: Combines images and audio - Expressive Visuals: Lifelike movements and emotions - Seamless Integration: Easy use with Kie.ai - High-Quality Rendering: Professional-grade output
4.9/ 5
55,773 ratingsSlide your rating
PoorExcellent
  • 01
  • 02
  • 03
  • 04
  • Wan 2.2 A14B Turbo API is part of the Wan 2.2 suite, enabling fast cinematic video generation from text or images at 480p or 720p, available through Wan 2.2 online API on Kie.ai.

    Kie.ai provides Wan 2.2 T2V API for text-to-video, Wan 2.2 I2V API for image-to-video and S2V for speech-to-video, all powered by the Wan 2.2 A14B Turbo API for smooth motion and cinematic fidelity.

    Turbo mode in Wan 2.2 turbo API accelerates rendering while preserving cinematic quality, making it ideal for rapid prototyping, marketing workflows, and automated pipelines.

    No. Through Wan 2.2 online API on Kie.ai, developers can call Wan 2.2 A14B API via REST endpoints without GPU setup, ensuring easy deployment and scalability.

    Create a key at kie.ai/api-key and send it as a Bearer token. Each video is an asynchronous task on POST https://api.kie.ai/api/v1/jobs/createTask with the model wan/2-2-a14b-text-to-video-turbo, wan/2-2-a14b-image-to-video-turbo or wan/2-2-a14b-speech-to-video-turbo, and the response returns a taskId. Pass a callBackUrl to receive the finished video, or poll Get Task Details with the taskId. Parameters are in the Wan 2.2 text-to-video and image-to-video API documentation.

    Yes. Kie.ai offers free Wan AI API testing, allowing developers to experiment with Wan 2.2 A14B Turbo API, T2V API, and I2V API before full integration.

    Text-to-video and image-to-video cost 8 credits per second ($0.04) at 480p and 16 credits per second ($0.08) at 720p. Speech-to-video costs 12, 18 or 24 credits per second ($0.06, $0.09 or $0.12) at 480p, 580p or 720p. Full rates are on the Kie.ai pricing page.价格可能会调整,请以本页顶部价格卡显示的价格为准。

    Text-to-video and image-to-video output 480p or 720p (default 720p), and text-to-video also takes a 16:9 or 9:16 aspect ratio; neither has a frame-rate setting. Speech-to-video supports 480p, 580p or 720p (default 480p), with frames_per_second from 4 to 60 (default 16) and num_frames from 40 to 120.

    Wan 2.2 image-to-video takes one image URL (JPEG, PNG or WebP, up to 10MB) and a text prompt of up to 5,000 characters, and outputs 480p or 720p video (default 720p). Optional settings are prompt expansion, a seed, and an acceleration level of none or regular; more acceleration is faster but lowers quality, so none is the recommended value. Text-to-video has the same 5,000-character prompt limit and takes a 16:9 or 9:16 aspect ratio.

    Wan 2.2 uses a larger training dataset and a Mixture-of-Experts (MoE) architecture, offering smoother motion, more stable camera control, and higher visual fidelity. Compared to Wan 2.1, Wan 2.2 API A14B achieves stronger performance across benchmarks like Wan-Bench 2.0.

    The Wan 2.2 weights are released under the Apache 2.0 license on GitHub and Hugging Face, but the official repo notes that single-GPU text-to-video with the A14B model needs a GPU with at least 80GB of VRAM. The Wan 2.2 API on Kie.ai runs the same A14B models in the cloud through one REST request, so you skip GPU setup.