display_media

Show Easy-Peasy.AI images in an embedded gallery or videos in an embedded player. Use IDs returned by generate_image, get_image, generate_video, or get_video. Can display a processing video and check its progress. Reads existing results in the connected account; does not generate content or spend credits. Clients without embedded UI still receive the media links.

read-only

Argument	Type	Description
ids*	array	Existing image or video IDs to display, in order (up to 8).
media_type*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "media_type",
    "ids"
  ],
  "properties": {
    "ids": {
      "type": "array",
      "items": {
        "type": "integer",
        "minimum": 1
      },
      "maxItems": 8,
      "minItems": 1,
      "description": "Existing image or video IDs to display, in order (up to 8)."
    },
    "media_type": {
      "enum": [
        "image",
        "video"
      ],
      "type": "string"
    }
  },
  "additionalProperties": false
}

generate_image

Generate or edit an image with Easy-Peasy.AI. Synchronous — returns image URL(s) when generation finishes (can take up to a few minutes). Uses image credits and requires a paid plan for API access. To edit existing images, pass their URLs in source_images; model then picks the edit model. display_media shows the returned image IDs in an embedded gallery.

Argument	Type	Description
model	string	Image model name. For new images, e.g. "Nano Banana 2" (default), "Nano Banana Pro", "FLUX.2 [max]", "OpenAI GPT Image 2.5 Flare Medium", "OpenAI GPT Image 2 Medium", "Seedream 5.0 Pro". With source_images, model also picks the edit model, so it must be one of the edit models (a subset), e.g. "Nano Banana 2", "Nano Banana Pro", "OpenAI GPT Image 2.5 Flare Medium", "OpenAI GPT Image 2.5 Sunburst Medium", "Seedream 5.0 Pro", "FLUX.2 [max]" or "Qwen Image"; any other name is rejected with the list of edit models. Omit model when editing to use "OpenAI GPT Image 2.5 Flare Medium".
style	string	Optional style preset name.
prompt*	string	Description of the image to generate.
outputs	number	Number of images to generate (default 1).
dimensions	string	Aspect ratio such as "1:1", "16:9" or "9:16" (supported ratios vary by model), or a pixel size "WIDTHxHEIGHT" such as "1792x1024" (default "1024x1024"). Nano Banana 2, Nano Banana Pro and GPT Image models map a pixel size to the nearest aspect ratio they support; other models may not, so prefer an aspect ratio.
resolution	string	For models that support it: "1K" or "2K".
source_images	array	Optional image URLs to edit/transform (image-to-image). Up to 10.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "prompt"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "Image model name. For new images, e.g. \"Nano Banana 2\" (default), \"Nano Banana Pro\", \"FLUX.2 [max]\", \"OpenAI GPT Image 2.5 Flare Medium\", \"OpenAI GPT Image 2 Medium\", \"Seedream 5.0 Pro\". With source_images, model also picks the edit model, so it must be one of the edit models (a subset), e.g. \"Nano Banana 2\", \"Nano Banana Pro\", \"OpenAI GPT Image 2.5 Flare Medium\", \"OpenAI GPT Image 2.5 Sunburst Medium\", \"Seedream 5.0 Pro\", \"FLUX.2 [max]\" or \"Qwen Image\"; any other name is rejected with the list of edit models. Omit model when editing to use \"OpenAI GPT Image 2.5 Flare Medium\"."
    },
    "style": {
      "type": "string",
      "description": "Optional style preset name."
    },
    "prompt": {
      "type": "string",
      "description": "Description of the image to generate."
    },
    "outputs": {
      "type": "number",
      "description": "Number of images to generate (default 1)."
    },
    "dimensions": {
      "type": "string",
      "description": "Aspect ratio such as \"1:1\", \"16:9\" or \"9:16\" (supported ratios vary by model), or a pixel size \"WIDTHxHEIGHT\" such as \"1792x1024\" (default \"1024x1024\"). Nano Banana 2, Nano Banana Pro and GPT Image models map a pixel size to the nearest aspect ratio they support; other models may not, so prefer an aspect ratio."
    },
    "resolution": {
      "type": "string",
      "description": "For models that support it: \"1K\" or \"2K\"."
    },
    "source_images": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Optional image URLs to edit/transform (image-to-image). Up to 10."
    }
  },
  "additionalProperties": false
}

generate_speech

Convert text to speech (ElevenLabs-powered). Synchronous — returns the audio file URL. Billed against the account’s monthly text-to-speech character quota.

Argument	Type	Description
text*	string	Text to speak.
speed	number	Playback speed 0.7-1.2 (default 1.0).
voice_id*	string	Voice id from list_voices.
output_format	string	Audio format, e.g. "mp3_44100_128" (default) or "wav".

Input schema (JSON)

{
  "type": "object",
  "required": [
    "text",
    "voice_id"
  ],
  "properties": {
    "text": {
      "type": "string",
      "description": "Text to speak."
    },
    "speed": {
      "type": "number",
      "description": "Playback speed 0.7-1.2 (default 1.0)."
    },
    "voice_id": {
      "type": "string",
      "description": "Voice id from list_voices."
    },
    "output_format": {
      "type": "string",
      "description": "Audio format, e.g. \"mp3_44100_128\" (default) or \"wav\"."
    }
  },
  "additionalProperties": false
}

generate_text

Generate text with an Easy-Peasy.AI template (preset). Synchronous — returns the generated text. Uses the account word quota and requires available API token allowance. Call get_template first to learn which fields a template accepts; pass template-specific fields via extra_fields (e.g. {"extra1": "..."}).

Argument	Type	Description
tone	string	Optional tone of voice, e.g. "Friendly".
preset*	string	Template slug, e.g. "blog-post-intro" (see list_templates).
outputs	number	How many variations to generate (default 1).
keywords	string	Main topic / input text for the template. Required by almost all templates.
language	string	Output language name in English, e.g. "English", "Spanish".
extra_fields	object	Template-specific fields keyed by field name from get_template, e.g. {"extra1": "value"}.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "preset"
  ],
  "properties": {
    "tone": {
      "type": "string",
      "description": "Optional tone of voice, e.g. \"Friendly\"."
    },
    "preset": {
      "type": "string",
      "description": "Template slug, e.g. \"blog-post-intro\" (see list_templates)."
    },
    "outputs": {
      "type": "number",
      "description": "How many variations to generate (default 1)."
    },
    "keywords": {
      "type": "string",
      "description": "Main topic / input text for the template. Required by almost all templates."
    },
    "language": {
      "type": "string",
      "description": "Output language name in English, e.g. \"English\", \"Spanish\"."
    },
    "extra_fields": {
      "type": "object",
      "description": "Template-specific fields keyed by field name from get_template, e.g. {\"extra1\": \"value\"}.",
      "additionalProperties": {
        "type": "string"
      }
    }
  },
  "additionalProperties": false
}

generate_video

Start an AI video generation. Defaults to MiniMax H3 Max: 5 seconds, 768p, native audio, 4 credits per second at 768p. With an image and no model, uses MiniMax H3 Max Image. ASYNC — returns a video id. display_media shows the video and checks its progress in an embedded player; get_video also checks that same id. Uses video credits (billed per second of output).

Argument	Type	Description
image	string	Optional image URL used as the first frame. With no model, selects MiniMax H3 Max Image. For an explicit model, select the matching Image variant.
model	string	Optional video model. Omit for "MiniMax H3 Max" (or "MiniMax H3 Max Image" when image is supplied). Other examples: "Veo 3.1", "Veo 3.1 Fast", "Seedance 2.5", "Seedance 2.0 Mini". An explicit model is used as supplied; choose its Image variant for image-to-video.
prompt*	string	Description of the video to generate.
duration	string	Clip length in seconds as a string. MiniMax H3 Max supports "5" through "15" (default "5"). Veo 3.1 supports only "4", "6", or "8" seconds. Must be supported by the selected model. If omitted, uses a supported model default.
resolution	string	Model-dependent output resolution. MiniMax H3 Max supports "768p" (default) or "480p". Other models may support "720p", "1080p", or "2k".
aspect_ratio	string	Aspect ratio, e.g. "16:9" (default), "9:16", "1:1".

get_account

Check connection status only when the user explicitly asks whether Easy-Peasy.AI is connected. Returns only a boolean. Do not call for general knowledge, account deletion, or requests for credentials or personal details; those requests are unsupported by this tool.

read-only

No arguments.

Input schema (JSON)

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

get_image

Get a previously generated image by its numeric id (returned by generate_image).

read-only

Argument	Type	Description
image_id*	number	Numeric image id.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "image_id"
  ],
  "properties": {
    "image_id": {
      "type": "number",
      "description": "Numeric image id."
    }
  },
  "additionalProperties": false
}

get_template

Get one text generation template by slug, including its input fields (name, label, type, options). Field names like "keywords" and "extra1".."extra14" map directly onto generate_text parameters.

read-only

Argument	Type	Description
slug*	string	Template slug from list_templates.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Template slug from list_templates."
    }
  },
  "additionalProperties": false
}

get_transcription

Get a transcription started with transcribe_audio using its exact returned uuid and the same connected account. The content field is empty until transcription finishes. If the job is not found or fails, report the error; do not start a replacement transcription unless the user explicitly requests a new job.

Argument	Type	Description
audio_id*	string	Transcription uuid from transcribe_audio.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "audio_id"
  ],
  "properties": {
    "audio_id": {
      "type": "string",
      "description": "Transcription uuid from transcribe_audio."
    }
  },
  "additionalProperties": false
}

get_video

Check a video generation started with generate_video. Returns { video: { id, url, status } } — status is "processing" until the video is ready, then "completed" with the download url.

read-only

Argument	Type	Description
video_id*	number	Video id returned by generate_video.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "video_id"
  ],
  "properties": {
    "video_id": {
      "type": "number",
      "description": "Video id returned by generate_video."
    }
  },
  "additionalProperties": false
}

list_templates

List a page of Easy-Peasy.AI writing templates (presets), optionally filtered by category. Returns slug, title, description, and category, plus total, categories, and next_offset (null on the last page). Use get_template to inspect a known slug directly, then generate_text to run it.

read-only

Argument	Type	Description
limit	integer	Maximum results to return (default 20, maximum 50).
offset	integer	Start position. Use next_offset from the previous result to read another page.
category	string	Optional category name to filter templates by.

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "default": 20,
      "maximum": 50,
      "minimum": 1,
      "description": "Maximum results to return (default 20, maximum 50)."
    },
    "offset": {
      "type": "integer",
      "default": 0,
      "minimum": 0,
      "description": "Start position. Use next_offset from the previous result to read another page."
    },
    "category": {
      "type": "string",
      "description": "Optional category name to filter templates by."
    }
  },
  "additionalProperties": false
}

list_voices

List a page of text-to-speech voices (id, name, language, accent), including the account’s custom/cloned voices. Filter by language and optionally accent. Returns total and next_offset (null on the last page). Choose a suitable returned id and pass it as voice_id to generate_speech; additional pages are optional.

read-only

Argument	Type	Description
limit	integer	Maximum results to return (default 20, maximum 50).
accent	string	Optional accent filter.
offset	integer	Start position. Use next_offset from the previous result to read another page.
language	string	Optional language filter, e.g. "Dutch".

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "default": 20,
      "maximum": 50,
      "minimum": 1,
      "description": "Maximum results to return (default 20, maximum 50)."
    },
    "accent": {
      "type": "string",
      "description": "Optional accent filter."
    },
    "offset": {
      "type": "integer",
      "default": 0,
      "minimum": 0,
      "description": "Start position. Use next_offset from the previous result to read another page."
    },
    "language": {
      "type": "string",
      "description": "Optional language filter, e.g. \"Dutch\"."
    }
  },
  "additionalProperties": false
}

transcribe_audio

Transcribe audio or video from a public link: a media file, or a page with a video or audio in it — YouTube, X (Twitter) posts and broadcasts, Instagram, TikTok, Google Drive, SoundCloud, Loom and most other video sites (up to 6 hours). ASYNC — returns a uuid once the job has started (checking a page link can take up to a minute); then poll get_transcription until the transcript is ready, which takes a few minutes for a long video. A link without a video or audio, or a private or live one, is usually refused at once with the reason; a download that fails later shows as status "failed" in get_transcription. Requires a paid plan.

Argument	Type	Description
url*	string	Public link to an audio/video file, or to a page with a video or audio on it (a YouTube video, an X post, an Instagram reel, a TikTok, a Google Drive file…).
name	string	Optional name for the transcription.
language	string	Spoken language name in English, e.g. "English" (helps accuracy).
detect_speakers	boolean	Label different speakers in the transcript (default true). When off, a YouTube video that has captions is transcribed from them at once.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "Public link to an audio/video file, or to a page with a video or audio on it (a YouTube video, an X post, an Instagram reel, a TikTok, a Google Drive file…)."
    },
    "name": {
      "type": "string",
      "description": "Optional name for the transcription."
    },
    "language": {
      "type": "string",
      "description": "Spoken language name in English, e.g. \"English\" (helps accuracy)."
    },
    "detect_speakers": {
      "type": "boolean",
      "description": "Label different speakers in the transcript (default true). When off, a YouTube video that has captions is transcribed from them at once."
    }
  },
  "additionalProperties": false
}

Easy-Peasy.AI

Try it

display_media Read-only

Easy-Peasy.AI

Try it

display_media Read-only

Tools (13)