LmaoAPIInstall

Summary

Generates text or images, or transcribes audio, using the LmaoAPI service. Choose a mode, provide its prompt or Binary input, and configure the relevant model and options; the node processes each input item and returns the service response or generated file.

Inputs

• Mode (required) — Select text generation, image generation, or audio transcription.
• Text generation (required) — Set the model ID and user prompt; the system prompt is optional. A non-empty incoming JSON text field is appended to the user prompt as reference document content. Optionally provide up to 10 reference images from the current item’s Binary data, named nodes, or image URLs.
• Image generation (required) — Set the user prompt and choose GPT-Image or Nano Banana. Configure the model-specific size or aspect ratio and available quality, background, and output format options. Reference images can come from Binary data or URLs; GPT-Image uses the edits endpoint when images are supplied.
• Audio transcription (required) — Provide an audio or video file in Binary data, from the current input or named nodes, and specify comma-separated Binary property names to check. The first matching supported file is used. Language and response format are hidden in this build; transcription uses the Omni backend.

Output shape

One output item per input item, paired with its source item.

Text mode returns the API response in JSON. Image mode returns JSON status and a generated image in Binary property data. Audio mode returns JSON with a text field containing timestamped Markdown transcription. Errors stop execution unless Continue On Fail is enabled, in which case an error object is returned.

Links

• n8n community nodes installation guide