Buble API

Server-side API for creating AI image and video generations with Buble.

Buble API

The Buble API lets you create AI image and video generations from your own backend. The public API is intentionally small: discover models, upload files, create asynchronous generation tasks, and poll the result.

Base URL

https://buble.ai

Public endpoints

MethodEndpointPurpose
GET/api/v1/modelsList API-ready models, public modes, inputs, and parameters.
POST/api/v1/filesUpload image, video, or audio assets for generation inputs.
POST/api/v1/generationsCreate an asynchronous generation task.
GET/api/v1/generations/[id]Query task status and result media.

Core workflow

  1. Authenticate with Authorization: Bearer $BUBLE_API_KEY.
  2. Pick a model and mode from GET /api/v1/models.
  3. Upload files first if the mode requires media input.
  4. Create a generation task.
  5. Poll the task until success or failed.

Public field model

Buble's public generation request is flat: put media URLs and model-specific controls directly in the JSON body.

FieldMeaning
modelStable model key, for example google/nano-banana-pro.
modePublic operation, for example text_to_image or frames_to_video.
promptText instruction for the generation.
image_urls, start_frame, end_frame, video_urls, audio_urlsSource media URLs for media-input modes.
model optionsModel-specific controls returned by /api/v1/models, such as duration, resolution, aspect_ratio, or output_format.

Do not send input, options, or internal implementation fields such as scene, sub_mode_id, provider, mediaType, or media_type. The API rejects these fields because Buble resolves them server-side from model, mode, and the flat public input fields.