Learning path
Multimodal AI
Vision with images and PDFs, speech to text and text to speech, and image generation, with animated films and runnable Python. Part of the Gen AI Developer premium track.
-
1
Vision: Sending Images and PDFs to a Model
Modern LLMs can read images, screenshots, charts, receipts and PDFs. Learn how to send them through the API (base64 and URLs), what they're good and bad at, image…
-
2
Speech to Text and Text to Speech
Add voice to AI apps: transcription with Whisper-style models, timestamps and Indian languages, text-to-speech voices, voice-assistant pipelines, latency budgets and audio basics in Python.
-
3
Image Generation APIs
Generate and edit images from text with APIs and open models: writing good image prompts, sizes and costs, editing and inpainting, safety filters, copyright and labelling AI-generated images.