Vimmerse Dev

Endpoints (25 live)

• POST /v2/audio/text-2-sound-effect — Generates a sound effect of the given length from a description, and returns the asset with the audio URL in results. (0.12 USDC on Base)
• POST /v2/image/face-swap — Swaps the faces in a target image with faces from one or more reference images. The first URL is the target and the rest are reference faces; order_indices maps target faces (left to right from 0) to references. Returns the asset with the output URL in results. (0.24 USDC on Base)
• POST /v2/image/elements — Generates or edits an image from a main image plus reference images of characters, objects or environments, guided by a prompt. The first URL is the main image and the rest are references. Returns the asset with the output URLs in results. Credits depend on the model tier and the quantity. (0.12 USDC on Base)
• POST /v2/audio/text-2-music — Generates a music track from a description with Lyria, and returns the asset with the WAV URL in results. (0.24 USDC on Base)
• POST /v2/video/lip-sync — Makes the face in an image or video speak: give audio_url, or a prompt and a voice for generated speech. Send async_mode true and poll GET /v2/asset/{asset_id}. Credits depend on the tool and the audio length. (1.2 USDC on Base)
• POST /v2/video/video-effects — Animates an image with a named motion effect such as BulletTime, with an optional second image for two-subject effects. Send async_mode true and poll GET /v2/asset/{asset_id}. Credits depend on the effects tool. (1.2 USDC on Base)
• POST /v2/image/try-on — Composites the clothing from one image onto the person in another image. Returns the asset with the output URL in results. (0.24 USDC on Base)
• POST /v2/image/image-2-image — Transforms or reimagines a source image from a public HTTPS URL with a text prompt, and returns the asset with the output URLs in results. Credits depend on the model tier and the quantity. (0.12 USDC on Base)
• POST /v2/video/crop-to-aspect-ratio — Crops a video to the given aspect ratio, from the center by default or from the given origin. Send async_mode true and poll GET /v2/asset/{asset_id}. (0.6 USDC on Base)
• POST /v2/workflow — Starts a workflow from a published template on your image URLs with the template's options, and returns the workflow object at once. Poll GET /v2/workflow/{workflow_id} until processing_status is success or fail, then read result (images) and media_result (video). Each run is charged the template's list price in credits for the selected pipeline mode, as listed by GET /v2/workflow/templates. (0.6 USDC on Base)
• POST /v2/video/sound-effect — Generates a sound effect described by the prompt and mixes it onto the video. Send async_mode true and poll GET /v2/asset/{asset_id}. (0.6 USDC on Base)
• POST /v2/video/replace-background — Composites a foreground video over a background image or video, with chroma key, scale, alignment and offset controls. Send async_mode true and poll GET /v2/asset/{asset_id}. (1.2 USDC on Base)
• POST /v2/video/enhance — Upscales a video by 2x or 4x and, or, cleans compression artifacts. Send async_mode true and poll GET /v2/asset/{asset_id}. (1.2 USDC on Base)
• POST /v2/story/images-2-video — Creates a story video from an idea and a list of image URLs: narration and music, one animated scene per image, and final composition. Returns the story object at once; poll GET /v2/story/{story_id} until status is success and read video_url. Credits are charged per second of scene video by tool tier, doubled with native audio. (3 USDC on Base)
• POST /v2/video/reframe — Reframes a video to a new aspect ratio with Luma, guided by a prompt, with optional grid and crop window fields. Send async_mode true and poll GET /v2/asset/{asset_id}. (1.2 USDC on Base)
• POST /v2/image/edit-image — Edits an image by one operation chosen with option: RemoveText, Upscale, ExpandToAspectRatio (outpaints to a new aspect ratio), Inpaint (regenerates the masked region from a prompt) or LumaReframe. Returns the asset with the output URLs in results. (0.12 USDC on Base)
• POST /v2/image/replace-background — Removes the background of an image (transparent PNG), replaces it with a second image, or restyles it after a style reference image. Returns the asset with the output URL in results. (0.12 USDC on Base)
• POST /v2/video/reference-to-video — Generates a video from one or more reference images and a prompt with the chosen tool, for 1 to 30 seconds. Send async_mode true and poll GET /v2/asset/{asset_id}. Credits depend on the tool tier and the duration in 5 second blocks. (1.2 USDC on Base)
• POST /v2/media — Queues a video generation job from a text prompt, optional reference media and an optional audio track, and returns the media object at once. Poll GET /v2/media/{media_id} until processing_status is success and read the URLs in result. Credits depend on the tool tier, the duration, the quantity and the audio options, and the estimate route returns the exact number. (1.2 USDC on Base)
• POST /v2/story/idea-2-video — Creates a complete video from a text idea in one job: storyboard, element and scene images, narration and music, animation and composition. Returns the story object at once; poll GET /v2/story/{story_id} until status is success and read video_url. Credits are charged per second of scene video by tool tier, doubled with native audio. (4.5 USDC on Base)

+5 more endpoints.