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 text · Level 3
2. Text-to-Speech: how AI gives text a voice · Level 3
3. Voice cloning: what you record is what you get · Level 3
4. ElevenLabs Dubbing: a recording in another language · Level 3
5. Music Finetunes: your own sound, on demand · Level 3
6. Virtual try-on: judging whether the picture got it right · Level 3
7. Diffusion models: from noise to video, inside a compressed space · Level 4
8. Flows: building content from connected nodes · Level 3

## Sources

These lessons draw on 14 sources. The most used:

- [ElevenLabs documentation](https://elevenlabs.io/docs/overview/intro)
- [Gemini API Documentation](https://ai.google.dev/gemini-api/docs)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://arxiv.org/abs/2212.04356)
- [Veo: a text-to-video generation system](https://storage.googleapis.com/deepmind-media/veo/Veo-3-Tech-Report.pdf)
- [ElevenLabs changelog](https://elevenlabs.io/docs/changelog)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://arxiv.org/abs/2112.10752)
- [OpenAI Cookbook (rendered site)](https://developers.openai.com/cookbook)
- [Video generation models as world simulators](https://openai.com/index/video-generation-models-as-world-simulators/)

[All units in Learn to use AI](https://rabbithole.pro/courses/learn-ai)

Source page: https://rabbithole.pro/courses/learn-ai/going-deeper-media