Name: iris

Speech-to-text (STT):

• visualisation, maybe spectrum waveform.

Text-to-speech (TTS):

• single voice.

**Video-to-text (

Visualisation:

• appearance.
• 1D model (by list of emotions), visualized by a single eye on the desktop.
• 2D model.
• 3D model.

AI:

• build local model with well-chosen architectural choices, requires more research.