Speech illustrator is an AI that listens to your spoken language of choice and generates fitting images.

Example applications are audiobooks, podcasts, songs, lectures, and conversations. All speech works.

The program is compatible with all device types and media platforms such, as Audible, Spotify, and Apple podcasts. The AI can interpret 90+ languages. Speech compatibility may vary, with English being interpreted the best. Check Open AI Whisper documentation for more information.

Troubleshooting: Slow internet connection may interfere with functioning. Try a longer Update Intervall Period.

To use the program follow these steps:

1. Update Intervall Period: How often do you want images to be generated?
2. Custom theme: optional preference for the art style. If left blank the AI adapts the style after the content.
3. Audio source: Do you want audio to be retrieved from your microphone or system audio? Allow access to the chosen audio source.
4. Make audio available: Start the audiobook, podcast, or make the speech of interest available to your device.
5. Click Play and enjoy after ~30 s initiation period.
6. Download icon: Save the generated image to your device.