Take a tour of the new automation blocks in your MindStudio workspace that allow you to generate images and audio within any workflow or chat.  

We’ve released new updates to dramatically enhance your AI applications — including new automations for image and audio models, and sort options to help you select the best model for every step of your AI workflow.  

New models

Generate images and audio directly within your AI applications or workspace assistant using DALL E and Text to Speech from OpenAI.

Generate images

• Create YouTube thumbnails
• Develop storyboards for ad pitches
• Visualize large datasets for easier interpretation
• Generate banner ad images

Text to speech

• Narrate blog posts and articles
• Assist customers with documentation via audio
• Create voiceovers for YouTube videos

Analyze image

• Analyze diagrams and flowcharts
• Convert physical invoices to CSV files
• Write code from design images

New workspace features

The Automations workflow has new automation blocks to help you integrate image and audio generation into your applications and automations. Plus, the application editor has new sorting options to help you choose the best model for each workflow step. 

Q&A

Ask questions about a particular use case or anything else you want to know relating to image and audio models. Learn what your peers in the MindStudio community are building. 

‍