Tool

​

What does it do?

Tools allow you to integrate external capabilities into your WordApp, expanding its functionality beyond text generation. They enable you to perform various tasks such as web searches, image generation, text-to-speech conversion, PDF parsing, and more.

By incorporating tools, you can create more dynamic and interactive WordApps that can access and process real-world data, generate multimedia content, and perform complex operations. This makes your WordApps more versatile and capable of handling a wide range of tasks and scenarios.

Start typing / in the editor and scroll down to the Tool section:

​

Available Tools

Tool Name	Description
Web Search with Exa	Query high-quality information from the internet
Website Similarity Search	Find similar websites to a given URL
Webscrape	Scrape data from a URL
Image Generation	Generate images using AI models
Text-to-Speech with ElevenLabs	Convert text to speech
Speech-to-Text with Deepgram	Convert speech to text
File Content Extractor	Extract text from various file formats
PDF Parser	Extract and analyze content from PDF files
URL Converter	Convert a URL into a format usable in a tool or prompt

---

​

Web Search with Exa

​

Description

Perform a high-quality web search and retrieve relevant information directly from the internet. This tool allows users to customize search queries, control the number of results, and filter by category for more precise results.

​

Inputs

• Query: The query to search for.

• Full page text: Include the full page text or just highlights.

• Number of results: Number of search results to return (between 1 and 10).

• Result category: Limit your results to a specific category of website (e.g., news, company, GitHub, etc.).

​

Outputs

• Search results: Displays the retrieved search results as markdown. Each result typically includes:
  • Title: The title of the web page or article.
  • Published date: The date the content was published.
  • Source: The source of the information.
  • Excerpts: Key excerpts or snippets from the retrieved web pages, which provide context and relevance to the query.

---

​

Website Similarity Search

​

Description

Find websites that are similar to a specified URL. This tool allows you to explore websites with comparable content, structure, or focus, helping you discover relevant alternatives or competitors.

​

Inputs

• URL: The URL of the website to find similar websites to.

• Number of results: Number of search results to return (between 1 and 10).

• Result category: Filter the results based on specific website categories (e.g., news, company, GitHub, etc.).

​

Outputs

• Similar websites: The tool outputs a list of websites that are similar to the URL provided, including:
  • Title: The title of the similar website.
  • Published date: The date when the site or its content was published or last updated.
  • Source: The website or platform where the content is hosted.
  • Excerpts: Key text excerpts or descriptions from the websites to provide context and relevance.

---

​

Webscrape

​

Description

Scrape the content from any website by providing its URL. The tool extracts the main text and structure of the web page, optionally including or excluding images, and returns the data in markdown format. This is useful for data extraction, content analysis, or research purposes.

​

Inputs

• URL: The URL of the website to scrape.

• Exclude images: A boolean option to exclude images from the scraping process. If set to true, the output will only include text and other non-image content.

​

Outputs

• Scraped data: The extracted data from the specified web page, including:
  • Title: The title of the web page.
  • URL source: The source URL of the content.
  • Content: The main text of the web page in markdown format, including headings, paragraphs, links, and other text elements.
  • Images (optional): Any image URLs included in the scraped content, unless excluded.

---

​

Image Generation

​

Description

Generate high-quality digital images based on a user-provided text prompt. This tool allows users to customize the aspect ratio and choose different models for image generation. The output is a unique digital image that reflects the provided prompt, ideal for creative projects, prototyping, or artistic exploration.

​

Inputs

• Prompt: A detailed text description that guides the image generation. The more specific and vivid the description, the closer the generated image will align with the user’s vision.

• Aspect ratio: Define the aspect ratio for the generated image (e.g., 16:9, 1:1). This allows flexibility in the image’s final presentation format.

• Model: Select from different image generation models like Flux Pro, Flux Schnell, or Stable Diffusion.

​

Outputs

• Generated image: The tool produces a fully rendered image based on the given inputs, displayed directly in the output section. This image can be used in any vision capable model.

---

​

Text-to-Speech with ElevenLabs

​

Description

Convert written text into natural-sounding speech using ElevenLabs’ advanced text-to-speech technology. This tool allows users to choose from a variety of voices, offering flexibility in tone, gender, and accent, to generate realistic audio from any text input.

​

Inputs

• Text: The text that you wish to convert into speech. The input can range from short phrases to longer passages, allowing for diverse use cases like announcements, tutorials, or interactive voice responses.

• Voice: Select the voice model to synthesize the speech. Choose from different pre-set voices (e.g., ‘Will (US male)’, ‘Emma (UK female)’), which vary in accent, tone, and gender.

​

Outputs

• Generated audio file: The tool produces an audio file of the spoken text, which can be played directly in the app, passed into audio-capable models like Google Gemini, or downloaded for use in external applications.

---

​

Speech-to-Text with Deepgram

​

Description

Convert audio recordings into accurate text transcriptions using Deepgram’s speech-to-text technology. This tool is ideal for transcribing meetings, interviews, lectures, and other audio content into readable and searchable text. It supports multiple languages and can optionally identify different speakers.

​

Inputs

• Audio file: The audio file you want to transcribe. This can be any audio recording, such as a speech, conversation, or presentation.

• Language: The language spoken in the audio file (e.g., ‘en’ for English, ‘es’ for Spanish). Use standard ISO language codes for accurate transcription.

• Speaker identification: A boolean option to enable or disable speaker identification. If set to true, the tool will differentiate between multiple speakers in the transcription.

​

Outputs

• Transcribed text: The text version of the audio file, presented in a readable format. It includes all spoken words, and if speaker identification is enabled, it will label different speakers.

---

​

File Content Extractor

​

Description

Extract and parse content from various file formats, such as CSV, TXT, JSON, etc. This tool is ideal for pulling raw data from files and converting it into usable text output. It is not compatible with PDF files; use the PDF Parser tool for PDFs instead.

​

Inputs

• File: The file to parse.

​

Outputs

• Extracted content: The raw content from the file, parsed and displayed for further use.

---

​

PDF Parser

​

Description

Extract and analyze content from PDF files effortlessly, including both text and images. The tool can parse PDFs into structured Markdown text or process each page as an image. It is ideal for workflows requiring text extraction, visual content processing, or page-by-page document interaction.

​

Inputs

• PDF file: Upload the PDF file to be processed.

• Include pages as images: Toggle this option to extract full-page screenshots. Useful for visually complex documents or models requiring image inputs.

• File language: Specify the language of the content in the PDF to improve the accuracy of Optical Character Recognition (OCR).

​

Outputs

• Markdown: The PDF content is converted into Markdown for easy ingestion into any model.

• Pages: A detailed breakdown of the PDF by page, allowing for interaction with both text and images. This output can only be used inside a loop, just mention @pdf.pages and we’ll set it up for you in the editor automatically!

  • Markdown: The per-page text output.

  • Images: If the page has detectable images, they will show up here.

  • Page as Image: When “Include pages as images” is enabled, you can obtain high-quality images of each page, which can be used for models that process visual data.

• Screenshots: Injects a list of screenshots from each page of the PDF into the prompt so that it can be consumed by models with vision capabilities.

---

​

URL Converter

​

Description

Convert a provided URL into a file, audio, or image reference that can be used in your WordApp. This tool is versatile and works with different types of media links, enabling seamless conversion from web-based resources.

​

Inputs

• Input URL: The URL to convert.

• Conversion type: The type of conversion to perform (e.g., file, audio, image).

​

Outputs

• Converted output: The tool outputs the file, audio, or image reference for use in other tools or as part of the flow.

---

​

Best Practices

1. Choose the appropriate tool for your task to ensure the best results.
2. Provide clear and specific inputs to get more accurate outputs.
3. Use @mentions to reference tool outputs in other parts of your WordApp.
4. Combine tools with other nodes like Loops or Conditionals for more complex workflows.

By effectively using tools, you can create powerful, multi-functional WordApps that leverage external data and services to provide rich, interactive experiences.