> ## Documentation Index
> Fetch the complete documentation index at: https://docs.easy-peasy.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Tools

> The 12 tools exposed by the Easy-Peasy.AI MCP server

Every tool maps to a documented [REST API](/api-reference/introduction) endpoint and is billed the same way.

| Tool                | Mode      | Description                                                                      |
| ------------------- | --------- | -------------------------------------------------------------------------------- |
| `get_account`       | sync      | Verify the connection; returns account id, email, and name.                      |
| `list_templates`    | sync      | List text templates (presets) with slugs and categories.                         |
| `get_template`      | sync      | Input fields of one template (`keywords`, `extra1`…`extra14`).                   |
| `generate_text`     | sync      | Run a template; returns the generated text.                                      |
| `generate_image`    | sync      | Generate or edit an image; returns URL(s). Paid plans only.                      |
| `get_image`         | sync      | Fetch a generated image record by id.                                            |
| `generate_video`    | **async** | Start a video generation; returns an `id`.                                       |
| `get_video`         | sync      | Poll a video by `video_id` until `status` is `completed`.                        |
| `list_voices`       | sync      | Text-to-speech voices, including your custom and cloned voices.                  |
| `generate_speech`   | sync      | Text-to-speech; returns the audio URL.                                           |
| `transcribe_audio`  | **async** | Start transcription of an audio or video URL; returns a `uuid`. Paid plans only. |
| `get_transcription` | sync      | Poll a transcription by `audio_id`.                                              |

Expand a tool below for its parameters. Parameters marked with `*` are required.

## Text generation

<AccordionGroup>
  <Accordion title="list_templates" icon="list">
    Lists the available templates plus the list of categories.

    | Parameter  | Type   | Description                          |
    | ---------- | ------ | ------------------------------------ |
    | `category` | string | Optional category name to filter by. |
  </Accordion>

  <Accordion title="get_template" icon="circle-info">
    Returns one template with its input fields (name, label, type, options). Field names such as `keywords` and `extra1`…`extra14` map directly onto `generate_text` parameters.

    | Parameter | Type   | Description                          |
    | --------- | ------ | ------------------------------------ |
    | `slug` \* | string | Template slug from `list_templates`. |
  </Accordion>

  <Accordion title="generate_text" icon="pen">
    Runs a template and returns the generated text. Uses the account word quota.

    | Parameter      | Type   | Description                                                                      |
    | -------------- | ------ | -------------------------------------------------------------------------------- |
    | `preset` \*    | string | Template slug, for example `blog-post-intro`.                                    |
    | `keywords`     | string | Main topic or input text. Required by almost every template.                     |
    | `tone`         | string | Tone of voice, for example `Friendly`.                                           |
    | `language`     | string | Output language name in English, for example `Spanish`.                          |
    | `outputs`      | number | How many variations to generate (default `1`).                                   |
    | `extra_fields` | object | Template-specific fields keyed by field name, for example `{"extra1": "value"}`. |
  </Accordion>
</AccordionGroup>

<Tip>
  Call `get_template` before `generate_text` so the agent knows which `extra_fields` a template expects.
</Tip>

## Images

<AccordionGroup>
  <Accordion title="generate_image" icon="image">
    Generates or edits an image and waits for the result — this can take a few minutes. Uses image credits and requires a paid plan.

    | Parameter       | Type      | Description                                                                  |
    | --------------- | --------- | ---------------------------------------------------------------------------- |
    | `prompt` \*     | string    | Description of the image.                                                    |
    | `model`         | string    | Model name, for example `Nano Banana 2`, `FLUX.2 [max]`, `Seedream 5.0 Pro`. |
    | `dimensions`    | string    | Size as `WIDTHxHEIGHT`, for example `1024x1024` (default).                   |
    | `outputs`       | number    | Number of images (default `1`).                                              |
    | `style`         | string    | Optional style preset name.                                                  |
    | `resolution`    | string    | `1K` or `2K`, for models that support it.                                    |
    | `source_images` | string\[] | Up to 10 image URLs to edit or transform (image-to-image).                   |
  </Accordion>

  <Accordion title="get_image" icon="magnifying-glass">
    | Parameter     | Type   | Description                                    |
    | ------------- | ------ | ---------------------------------------------- |
    | `image_id` \* | number | Numeric image id returned by `generate_image`. |
  </Accordion>
</AccordionGroup>

## Video

<AccordionGroup>
  <Accordion title="generate_video" icon="video">
    Starts a generation and returns an id immediately. Billed per second of output.

    | Parameter        | Type    | Description                                                      |
    | ---------------- | ------- | ---------------------------------------------------------------- |
    | `prompt` \*      | string  | Description of the video.                                        |
    | `model` \*       | string  | Model name, for example `Veo 3.1`, `Seedance 2.0`, `Kling 2.5`.  |
    | `duration`       | string  | Clip length in seconds as a string, for example `"5"` (default). |
    | `aspect_ratio`   | string  | For example `16:9` (default), `9:16`, `1:1`.                     |
    | `resolution`     | string  | `480p`, `720p`, or `1080p` (model-dependent).                    |
    | `image`          | string  | Image URL used as the first frame (image-to-video).              |
    | `generate_audio` | boolean | Generate a soundtrack, on models that support audio.             |
  </Accordion>

  <Accordion title="get_video" icon="clock">
    Returns `{ video: { id, url, status } }`. `status` stays `processing` until the video is ready, then becomes `completed` with a download `url`.

    | Parameter     | Type   | Description                      |
    | ------------- | ------ | -------------------------------- |
    | `video_id` \* | number | Id returned by `generate_video`. |
  </Accordion>
</AccordionGroup>

## Speech

<AccordionGroup>
  <Accordion title="list_voices" icon="microphone-lines">
    Returns voices with id, name, language, and accent, including your custom and cloned voices.

    | Parameter  | Type   | Description                                    |
    | ---------- | ------ | ---------------------------------------------- |
    | `language` | string | Optional language filter, for example `Dutch`. |
    | `accent`   | string | Optional accent filter.                        |
  </Accordion>

  <Accordion title="generate_speech" icon="volume-high">
    Converts text to speech and returns the audio file URL. Billed against the monthly text-to-speech character quota.

    | Parameter       | Type   | Description                                             |
    | --------------- | ------ | ------------------------------------------------------- |
    | `text` \*       | string | Text to speak.                                          |
    | `voice_id` \*   | string | Voice id from `list_voices`.                            |
    | `speed`         | number | Playback speed between `0.7` and `1.2` (default `1.0`). |
    | `output_format` | string | For example `mp3_44100_128` (default) or `wav`.         |
  </Accordion>
</AccordionGroup>

## Transcription

<AccordionGroup>
  <Accordion title="transcribe_audio" icon="waveform">
    Starts a transcription of an audio or video file and returns a uuid immediately. Requires a paid plan.

    | Parameter         | Type    | Description                                                                |
    | ----------------- | ------- | -------------------------------------------------------------------------- |
    | `url` \*          | string  | Public URL of the audio or video file.                                     |
    | `language`        | string  | Spoken language name in English, for example `English`. Improves accuracy. |
    | `detect_speakers` | boolean | Label different speakers (default `true`).                                 |
    | `name`            | string  | Optional name for the transcription.                                       |
  </Accordion>

  <Accordion title="get_transcription" icon="file-lines">
    The `content` field stays empty until the transcription finishes.

    | Parameter     | Type   | Description                                 |
    | ------------- | ------ | ------------------------------------------- |
    | `audio_id` \* | string | Transcription uuid from `transcribe_audio`. |
  </Accordion>
</AccordionGroup>

## Async tools

`generate_video` and `transcribe_audio` return an id immediately instead of waiting for the result. Poll the matching `get_video` or `get_transcription` tool every 15–30 seconds until the result is ready.

Videos typically take 1–5 minutes depending on model, duration, and resolution.

## Account

<Accordion title="get_account" icon="user">
  Takes no parameters. Returns the authenticated account id, email, and name — use it to confirm the connection works.
</Accordion>