Elucidator｜AI Visual Assistant

Elucidator describes what your iPhone or iPad camera sees, on screen and aloud, using on-device AI. Use supported webcams or RTSP cameras and switch AI profiles to suit your task. Analyze images offline on supported devices without uploading them to an AI server. ---------- ■ Analyze What Your Camera Sees Analyze at regular intervals, manually or with Motion detection. Results appear over the camera preview. Streaming output shows text as it is generated. Preview text size and display options in Settings. Haptic feedback signals new results. The app analyzes live camera images, not saved video. ---------- ■ Hear Descriptions Aloud Turn speech on or off at any time. Adjust the voice and speaking rate, or enable “Wait for speech to finish” to hear the full description before the next analysis. Highlight spoken text to follow along on screen. ---------- ■ Set Up AI Profiles Choose from eight built-in AI profiles: • Describe the scene • Main objects and positions • Readable text • Clothing and appearance • Tidying and organization • Plant observation • Visual assistance • Compare two images Save and edit prompts, triggers, analysis intervals and image counts as AI profiles. Switch profiles without setting everything up again. Compare up to three images to describe changes. ---------- ■ Choose Your Camera and Analysis Area Analyze the full view or, with features unlocked, adjust the area shown on screen. Switch front/rear cameras, use macro on supported devices, mirror the front camera, pinch to zoom, tap to focus or lock focus and exposure. With features unlocked, use a UVC USB webcam on a compatible iPad or an RTSP network camera (IP camera). Save connections and select them from a list. ---------- ■ Review Recent Results While the app is open, review the last 50 results with their images, times and prompts. History is cleared when the app closes. Elucidator does not capture or save photos or videos. ---------- ■ Connect with Other Apps and Tools Use the GET API to retrieve results, images, and app and device status from a computer or another app on the same network. Results and status are available as JSON for your tools. With curl notifications, send results to an HTTP/HTTPS destination when analysis finishes. Set up requests in curl format and choose what to send: analysis text, images, prompts, completion time or device status. View API documentation, run requests, set notification frequency and send test notifications in the app. Use results in your own tools, logs or workflows. curl notifications are off by default. Only the information you select is sent outside your device when enabled. AI image analysis still runs on your device. ---------- ■ On-Device AI Image Analysis A VLM (vision-language model) understands images and generates descriptions. Elucidator uses Apple Intelligence’s AFM 3 Core and AFM 3 Core Advanced through Foundation Models. The model varies by device and OS. AI analysis works offline without sending images or descriptions to an AI server. curl notifications, ads, purchase checks and support pages may use the internet. ---------- ■ Useful For • Understanding scenes through text or speech • Finding objects and reading visible text • Exploring outfits, rooms and plants • Receiving visual information aloud • Analyzing webcam or RTSP camera feeds • Connecting your tools via the GET API or curl notifications • Exploring generative AI, VLMs and Apple Foundation Models Turn what you see into words, for everyday tasks or AI experiments. ---------- AI results may be inaccurate. For medical, safety or navigation decisions, verify the actual situation rather than relying on AI alone. Requires a supported OS and device with Apple Foundation Models available. Models and features may vary by device and OS. Terms of Use (Apple Standard EULA): https://www.apple.com/legal/internet-services/itunes/dev/stdeula/