Back to Roadmap

Phase 24

Voice & Multimodal Agents

STT, TTS, realtime voice, and agents that understand images, audio, video, PDFs, and screens.

8 modules

Estimated read time is shown per module based on lesson length.

Modules

1.STT~3 min read

2.TTS~2 min read

3.Realtime Voice~3 min read

4.Image Agents~3 min read

5.Audio Agents~3 min read

6.Video Agents~3 min read

7.PDF Agents~3 min read

8.Screen Understanding~3 min read

Phase 24 Glossary

40 terms · search to look up

Navigation

← Browser & Computer Use Agents Enterprise AI →