Automatically detects and blurs faces, license plates, and other identifiable features in an uploaded image to protect personal privacy.

Analyzes a given text for spelling and grammar errors and provides suggested corrections for any mistakes found.

Checks your text for plagiarism by comparing it to online sources and highlights any matching content found.

Compares two facial images to check if they are of the same person and provides a similarity score.

Sends a prompt to Eden AI, which remembers previous conversation context on the server, allowing you to continue the conversation with follow-up prompts without needing to resend the entire chat history.

Removes a response that was previously saved in the system.

Analyzes an image to identify if it was created by artificial intelligence or captured as a real photograph.

Analyzes a given text to identify if it was authored by a human or generated by an artificial intelligence or large language model.

Analyzes an image to determine if it has been altered or generated by artificial intelligence, such as a deepfake.

Analyzes an image to detect and identify potentially inappropriate or explicit content, such as nudity, violence, or gore.

Analyzes an image to identify faces and provides detailed information such as estimated age, gender, emotional state, facial landmarks, accessories worn, and image quality metrics.

Analyzes text using AI moderation to detect offensive, explicit, hateful, violent, or self-harm-related content.

Detects and pinpoints the presence of recognized brand logos within a provided image.

Analyzes an image to identify and pinpoint objects, providing object labels, confidence scores, and the coordinates of bounding boxes around each detected object.

Analyzes a text to detect and extract specific named entities such as people, locations, organizations, dates, and similar information.

Extracts detailed tables, including individual rows and columns, from a PDF or image file. The processing is managed asynchronously by Eden AI.

Extracts detailed text information from each page of a multi-page PDF, including page numbers and individual word data, using Eden AI's internal asynchronous processing.

Uses OCR to recognize and extract text from one image, such as a photo of a sign or a screenshot.

Automatically analyzes a piece of text to detect and highlight its primary topics and key themes.

Creates a video based on your text prompt or a combination of text and a reference image, with Eden AI managing the processing and delivering the completed video.

Creates a new image based on your text description using AI image generators such as DALL·E, Stable Diffusion, Leonardo, and others.

Fetches a specific response that was previously saved, using its unique ID.

Retrieves a comprehensive list of all supported chat models (such as GPT, Claude, Gemini, etc.) along with detailed information about each model’s features and capabilities.

Retrieves a comprehensive list of all available features and their corresponding subfeatures provided by Eden AI.

Retrieves a list of available providers, their models, and associated pricing options for a selected feature or subfeature.

Sends a custom authenticated request to any specified Eden AI API endpoint.

Extracts and organizes detailed information such as personal details, education history, work experience, skills, languages, and certifications from a resume or CV.

Extracts and organizes key information, such as name, date of birth, and document number, from identification documents like passports, driver’s licenses, and national ID cards.

Extracts detailed, organized information such as merchant details, customer information, itemized lists, totals, payment details, and bank information from invoices or receipts.

Removes the background from an image file, isolating and keeping only the primary subject in the foreground.

Sends a user-defined message to an AI chat model (such as GPT, Claude, Gemini, or Llama) and retrieves the model's generated response, with automatic fallback options if the primary model is unavailable.

Transforms written text into spoken audio files by utilizing text-to-speech (TTS) service providers.

Transcribes audio recordings into written text, with features like identifying different speakers, using custom vocabulary, and choosing from multiple transcription providers (such as Whisper, Deepgram, AssemblyAI). Eden AI manages the background processing, so the module delivers the complete transcript once it's ready.

Translates the content of PDF, DOCX, or PPTX documents into another language while maintaining the original formatting and layout.

Translates a given text from one language to another specified language.

Uploads a file (such as a PDF, audio, image, or document) to Eden AI, making it available for use in other modules and providing a file ID that remains valid for 7 days.