Over the last few weeks, I've been prototyping an idea I had: everyone was creating images with AI text prompts, and they are/were all in English.
Since I use an AI service with many capabilities, I thought I could use it to create a chain of AI services that generate images with speech/voice (in (almost) any language) as input.
My PoC works - the first layer does the speech recognition, the second layer translates the recognized text into English, and the third layer generates an image from the "prompt".
To accomplish this, the TextUnbox REST API has received three new endpoints:
Whant to see it in action? Here it is: https://textunbox.app/#demo
Would you like to try it out? Write me a message. :)
As always, stay tuned, I'm working on more ideas.