Elucidator｜AI Visual Assistant
On-Device Talking AI Camera
Free · In‑App Purchases · Designed for iPad. Not verified for macOS.
Elucidator describes your iPhone or iPad camera view in text and speech with on-device AI. Use supported webcams or RTSP cameras and task-specific AI profiles.
On-device AI works offline without uploading images.
----------
■ Analyze What Your Camera Sees
Analyze at regular intervals, manually or with Motion detection.
Results overlay the camera view, with streaming text as it is generated. Preview text size and display settings. Hide results automatically or by swiping sideways. Adjust the edge effect’s colors, thickness and animation during inference.
Haptics signal new results. External displays offer “Text only” or “Image & text”. Analysis uses live camera images, not saved video.
----------
■ Hear Descriptions Aloud
Turn speech on/off and adjust voice and rate. “Wait for speech to finish” defers the next analysis. Highlight spoken text to follow along.
----------
■ Set Up AI Profiles
Choose from eight built-in 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, intervals and image counts in reusable AI profiles. Compare up to three images for changes.
----------
■ Choose Your Camera and Analysis Area
Analyze the full view or adjust the visible area with features unlocked.
Select “Circle to analyze” in an AI profile to outline an area. Adjust outside visibility, selection correction and cropping.
Switch front/rear cameras, use macro on supported devices, mirror the front camera, pinch to zoom, tap to focus or lock focus and exposure.
Unlock features to use UVC USB webcams on compatible iPads or RTSP IP cameras. Save and select connections.
----------
■ Review Recent Results
View the last 50 results with images, times and prompts. History clears when the app closes. No photos or videos are captured or saved.
----------
■ Connect with Other Apps and Tools
The GET API provides images plus results, app status and device status as JSON on the same network.
The Control API starts/stops analysis and changes prompts from the same network. APIs require the app in the foreground.
curl notifications send results after analysis to an HTTP/HTTPS address. Configure curl requests to send text, images, prompts, completion time or device status.
View API documentation, run requests, set notification frequency and send test notifications in the app.
You can also analyze images with external AI via OpenAI-compatible APIs. Potential connections include the OpenAI API (models behind ChatGPT), Gemini and Claude. Save multiple connections and models to switch between them and on-device AI.
Note: External AI integration tested with vLLM. Compatibility varies by service and model.
Unlock external integrations to use these features. curl notifications are off by default and send only selected data.
----------
■ On-Device AI Image Analysis
A VLM (vision-language model) describes images. On-device AI uses Apple Intelligence’s AFM 3 Core or AFM 3 Core Advanced via Foundation Models, depending on device and OS. It works offline without sending images or descriptions to AI servers.
External AI sends images and prompts to your configured endpoint; API fees may apply. External AI, curl notifications, ads, purchase checks and support pages use the network.
----------
■ Useful For
For scene descriptions, reading text, visual assistance, webcam/RTSP analysis, tool integrations and exploring generative AI, VLMs and Foundation Models.
----------
AI results may be inaccurate. For medical, safety or navigation decisions, verify the actual situation rather than relying on AI alone.
On-device AI 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/
Ratings & Reviews
- This app hasn’t received enough ratings or reviews to display an overview.
- Minor fixes and improvements to usability and stability
The developer, kentaro hirahara, indicated that the app’s privacy practices may include handling of data as described below. For more information, see the developer’s privacy policy .
Data Used to Track You
The following data may be used to track you across apps and websites owned by other companies:
- Purchases
- Location
- Identifiers
- Usage Data
- Diagnostics
Data Linked to You
The following data may be collected and linked to your identity:
- Purchases
- Location
- Identifiers
- Usage Data
- Diagnostics
Accessibility
The developer has not yet indicated which accessibility features this app supports. Learn More
Information
- Seller
- kentaro hirahara
- Size
- 14 MB
- Category
- Photo & Video
- Compatibility
Requires iOS 27.0 or later.
- iPhone
Requires iOS 27.0 or later. - iPad
Requires iPadOS 27.0 or later. - Mac
Requires macOS 27.0 or later and a Mac with Apple M1 chip or later. - Apple Vision
Requires visionOS 27.0 or later.
- iPhone
- Languages
English and 7 more
- English, French, German, Japanese, Korean, Portuguese, Simplified Chinese, Spanish
- Age Rating
4+
- 4+
- Contains
Advertising
- In-App Purchases
Yes
- Features + No Ads $8.99
- Unlock General Features $5.99
- Unlock External Integrations $6.99
- 機能解放 $5.99
- 機能解放＋広告削除 $8.99
- 機能解放＋広告削除（月額） $1.99
- 広告削除 $3.99
- Copyright
- © 2026 Kentaro Hirahara