Screenshot URL

Capture a screenshot of any web page and generate a public link to the image. Accepts a URL as input, takes a screenshot with customizable dimensions and format, stores it in cloud storage, and returns the public URL and file path of the screenshot.

Event Image for Event

Generates a custom event poster image and provides a shareable URL. Accepts event title, date, description, and an optional style reference as input, then crafts a detailed image prompt, uses OpenAI’s image model to create the poster, uploads it to cloud storage, and returns the image URL.

Generate Image (OpenAI)

Generate images from text prompts using AI, then store and return a shareable file link. Accepts a prompt describing the desired image, optional reference images, and settings for quality, size, and quantity; outputs a URL to the generated image file in cloud storage.

ElevenLabs Text-to-Speech

Convert written text into natural-sounding speech audio. Accepts a text string as input, uses ElevenLabs' API to synthesize speech with customizable voice and audio settings, and returns a URL to the generated MP3 audio file.

The Great Big Quiz of Everything

Create interactive, audio-enabled quizzes on any topic. Includes full video tutorial allowing you to build AI-powered, Supabase-secured, and fully adaptive quizzes on literally any topic you can imagine.

Generate Image from Reference

Generate custom images from a text prompt and optional reference images. Accepts a prompt describing the desired image and an array of reference images, then creates the image using OpenAI Image Generator, uploads it to cloud storage, and returns a URL link to the generated file.

Generate Music (Replicate)

Generate original music tracks based on a text description of style, mood, and instruments. Accepts a prompt describing the desired music and a duration in seconds, then returns a link or file containing the generated music track.

Voice-to-Voice Translation

Converts spoken audio into translated speech in another language. Accepts an audio file and a target language, transcribes the audio using OpenAI Whisper, translates the text with GPT, synthesizes the translated speech using OpenAI TTS, uploads the audio, and returns the transcription, translation, and a link to the new audio file.

Scrape YouTube Mentions

Finds recent YouTube videos mentioning a specific brand. Accepts a brand name, number of days to look back, and a results limit as input, then queries YouTube for videos published since the specified date that mention the brand. Returns a list of matching video details. The tool calculates the relevant date, fetches and filters YouTube videos using the YouTube Data API, and outputs structured results.

Generate Podcast on Competitors

Create a 1-minute podcast script summarizing a company's top competitors in a specific business context. Accepts the company name and industry, researches up-to-date competitor insights, generates a concise podcast script, and provides both the script text and an audio file as output.

Voice Transcription

Converts a voice audio file into text with detailed timestamps. Accepts a voice file as input, uses OpenAI Whisper to transcribe the audio and segment it by timestamps, and returns the full transcription along with timing information. The process involves uploading the file and receiving structured text output.

Asset Promotional Mobile Store

Generate a promotional Play Store asset image using a provided screenshot, title, and subtitle. Accepts a screenshot file (base64 or external URL), a title, and a subtitle as input, then returns a downloadable image file ready for Play Store use.