This is a speech-to-image notebook written using Google Cloud speech and translate APIs and DeepAI stable-diffusion image generation API. Any of the supported languages can be spoken and recorded natively, and will be used to generate images. Since most AI image generation APIs expect English-language input, here speech is transcribed in the spoken language, then translated to English, and then used to generate images.
danmohad/multiLangSpeechToImage_gc
Speech to image notebook using Google Cloud speech and translate APIs and DeepAI stable-diffusion image generation
Jupyter Notebook