AI Video and Audio Generation
Runway, Sora-style video, voice cloning and AI music for creators.
Taught by Asha Karki · AI Product Engineer
What you'll learn
- Choose the right AI video, voice, avatar and music tool for a given brief and budget
- Write shot-level prompts and use image-to-video to keep characters and products consistent
- Produce a clean voiceover from a script, including a consented voice clone where appropriate
- Build a talking-head or avatar explainer video and localise it into another language
- Generate accurate captions with Whisper and assemble video, voice, music and subtitles
- Apply disclosure, consent and copyright rules for synthetic media before publishing
About this course
Video and audio are the fastest-moving corner of generative AI, and creators who learn the workflows now have a real advantage. This intermediate course is for content creators, marketers, educators and small studios who want to produce short videos, voiceovers, avatars, captions and music with AI tools and finish with something publishable. You will plan shots for text-to-video and image-to-video models such as Runway, Sora, Veo and Kling, record or clone a voice responsibly with tools like ElevenLabs, build talking-head explainers with avatar platforms, generate captions with Whisper, add AI music and assemble everything in an editor. A full lesson covers deepfake law, platform disclosure rules and consent so your work stays trustworthy. You should already be comfortable with basic video editing and with using an AI chat assistant; no programming is required, though two lessons include short command-line examples.
Course content
6 lessons- 1The AI Video and Audio Landscape in 2026What each class of tool does well, what it still cannot do, and how a modern creator workflow fits together.Preview
- 2Text-to-Video and Image-to-Video WorkflowsWrite shot-level prompts, use starting frames for consistency and manage the regenerate-and-select loop.
- 3Voiceovers, Voice Cloning and Audio CleanupProduce clean narration from a script, clone a voice with consent and fix real recordings with AI.
- 4Avatars, Talking Heads and AI DubbingBuild presenter videos from a script and translate them into other languages with lip sync.
- 5Captions, Music and Assembling the Final VideoGenerate accurate subtitles with Whisper, add AI music legally and assemble everything in an editor.
- 6Ethics, Disclosure and the Law for Synthetic MediaConsent, deepfake rules, platform labels and copyright so your videos are trusted and legal.