Skip to main content

​
Overview

The Easy-Peasy.AI API lets you programmatically access our AI-powered tools:
  • Presets — Discover available text generation templates and their input fields
  • Text Generation — Generate blog posts, social media captions, emails, marketing copy, and more using text templates
  • Image Generation — Generate and edit images with Nano Banana, GPT Image, FLUX, Seedream, and other models
  • Video Generation — Generate videos with MiniMax H3 Max, Seedance 2.5, Gemini Omni, Veo, Kling, and other video models
  • Transcription — Transcribe audio files with speaker detection and enhanced quality
  • Text-to-Speech — Convert text to natural-sounding speech with public and custom voices
  • Chat Completions — OpenAI-compatible chat completions endpoint (works with OpenAI SDK)
  • Bots — Chat with your custom AI bots via API

Using an AI agent?

Easy-Peasy.AI also runs an MCP server at https://easy-peasy.ai/mcp — connect Claude, Cursor, Windsurf, or any MCP client without writing API code.

​
Authentication

Authenticated REST requests use your API key in the x-api-key header. Chat Completions also accepts Authorization: Bearer YOUR_API_KEY. TTS Config and public TTS Voices work without a key; custom voices require authentication. The separate Bots API documents its own headers. Keep API keys on your server, outside browser bundles and public repositories.

Get your API key

Generate an API key from your Easy-Peasy.AI settings page.

​
Base URL

All API requests are made to:
The Bots API uses a separate base URL:

​
Text generation workflow

  1. Discover presets — Call GET /api/presets to list available templates
  2. Get field requirements — Call GET /api/presets/{slug} to see what fields a preset needs
  3. Generate content — Call POST /api/generate with the preset slug and required fields

​
Media generation workflow

  1. Choose the exact model and inputs. For video, consult the model reference. Plan access and credit requirements depend on the model and settings.
  2. Submit once and save the ID. Videos and transcriptions run asynchronously. Standard image integrations wait for results, while some legacy integrations return pending records.
  3. Read or poll the result. Follow each endpoint’s response shape and polling example. Keep existing IDs when a local timeout occurs; submitting again can create another billable job.

​
Endpoints

List Presets

Discover available text generation templates.

Get Preset Details

Get input fields and constraints for a preset.

Generate Text

Generate content using any preset.

Generate Image

Generate or edit images using an exact model name.

Generate Video

Generate videos from text, images, or reference media.

Create Transcription

Transcribe audio files to text.

Text-to-Speech

Convert text to natural speech.

Chat Completions

OpenAI-compatible chat completions endpoint.

Chat with Bot

Interact with your custom AI bots via API.

MCP Server

Connect AI agents with the Model Context Protocol.