Going deeper

Going deeper: media

Going deeper: media is a unit of 8 lessons in Rabbithole's Learn to use AI course, at levels 3 to 4.

Lessons

1. Speech recognition: from sound to textLevel 3
2. Text-to-Speech: how AI gives text a voiceLevel 3
3. Voice cloning: what you record is what you getLevel 3
4. ElevenLabs Dubbing: a recording in another languageLevel 3
5. Music Finetunes: your own sound, on demandLevel 3
6. Virtual try-on: judging whether the picture got it rightLevel 3
7. Diffusion models: from noise to video, inside a compressed spaceLevel 4
8. Flows: building content from connected nodesLevel 3

Sources

These lessons draw on 14 sources. The most used:

• ElevenLabs documentation
• Gemini API Documentation
• Robust Speech Recognition via Large-Scale Weak Supervision
• Veo: a text-to-video generation system
• ElevenLabs changelog
• High-Resolution Image Synthesis with Latent Diffusion Models
• OpenAI Cookbook (rendered site)
• Video generation models as world simulators

All units in Learn to use AI