AI Video APIs

Integrate Seedance 2.5 video generation into your app. Generate from text or a starting image, then combine image, video, and audio references in the multimodal workflow.

Integrate single-face replacement into your video workflow. Submit a clip and reference face image, select the tracked face to replace, and retrieve the completed video through an asynchronous task.

Add Kling video generation to your app with text or image inputs. Build single shots or multi-shot sequences, define starting and ending frames, and control duration and audio in your API requests.

Integrate text-to-video and image-to-video generation with PixVerse. Send a prompt or starting image, then configure clip length, resolution, and audio to fit the video workflow in your application.

Add Hailuo video generation to your app using text prompts or a starting image. Request six- or ten-second clips and enable or disable prompt expansion in each API call.

Build video generation workflows with MiniMax H3 using text, starting and ending frames, or image, video, and audio references. Configure clip duration and resolution in the request to match your application.

Integrate Grok video generation with text prompts or image inputs. Request six- or ten-second clips from text, or use the image mode for clips up to thirty seconds with configurable framing and resolution.

Build Sora 2 video workflows with text prompts and optional starting images. Choose between two API contracts for portrait or landscape output, with storyboard controls available on the model route.

Integrate Wan video generation for prompts, starting images, or media references. Use the standard capability for text-only requests, or Wan 3.0 for image and reference workflows with optional audio generation.

Add Seedance video generation to your app with text prompts and frame inputs. Use the Seedance 2.0 API to guide generation with image, video, and audio references, plus duration and resolution controls.

Build image animation into your app with the Midjourney Video API. Submit a source image and motion prompt, choose low or high motion, and configure an ending frame or loop setting.

Add Vidu video generation to your app from text or image references. Configure style and movement in text mode, or supply up to seven images with optional audio in the image workflow.

Integrate Veo 3.1 video generation with text prompts, starting images, and optional ending frames. Request four-, six-, or eight-second clips with explicit controls for framing, resolution, and audio in your application.

Add SkyReels text-to-video and image-to-video generation to your app. Configure clip duration and resolution, and enable or disable prompt optimization directly in the request to support your video workflow.

Build video generation into your app with HappyHorse. Accept text prompts, a starting image, or up to nine image references, then configure clip duration and resolution for the selected input workflow.

Add image-to-video generation to your app with Runway. Send a source image URL and motion prompt, then request a five- or ten-second clip through a compact API payload.

Add multi-face swapping to your photo and video app. Map each target face to a reference image, with support for up to 20 mappings per photo and four per video.

Integrate head replacement into photo and video editing workflows. Send a target asset with one to four reference images, and use an optional prompt to describe the requested change.

Build video generation into your app from text prompts or a starting image. Set duration, aspect ratio, and resolution, with an optional ending image for image-to-video requests.

Add video transformation to your app with prompt-based editing or a dedicated anime conversion endpoint. Submit the inputs for your chosen workflow, set output options, and retrieve the processed clip.

Add video extension to your editing workflow. Submit a source clip and a prompt describing the continuation, configure duration and resolution, and retrieve the generated video for your app.

Add background removal to your video processing workflow. Submit a source video URL, track the processing task, and retrieve the edited clip for use in your application.

Integrate video watermark removal with separate endpoints for direct video URLs and Sora page links. Submit the matching source, track its job, and retrieve the processed video for your workflow.

Build photo dance features into your app using a subject image and a dance reference video. Submit both asset URLs and retrieve the generated video for playback in your interface.

Add motion transfer to your animation workflow with a character image and a driving video. Use the clip as the motion reference and retrieve the resulting character animation.

Add lip sync to image and video workflows, or build talking-photo features with image, audio, and text inputs. Use the corresponding endpoint to retrieve a generated video for your app.

Add automatic subtitle generation to your video workflow with a source video URL. Track the processing task and retrieve the subtitled video for playback or further use in your app.

Add video upscaling to your media processing pipeline. Submit a source video URL, set a 2x or 4x scale, and retrieve the enlarged clip for your application.