Skip to main content

Mazix Studios

MazixStudios

Generative AI

Generative here means the guidance is produced for this moment, from the step and the scene, then spoken. It is not a generic chatbot.

What is included

  • Speech to text on the session
  • A generated prompt for the next action
  • Text to speech back to the operator
  • Whisper, Vosk, and hosted speech where each one fits
  • A written line left behind for the record

Typical stack

  • Whisper
  • Vosk
  • Gemini
  • Speech to text
  • Text to speech
  • On-device speech
  • Hosted speech
  • Python
  • Spoken guidance
  • Prompt generation
  • Session transcript
  • Audio playback
  • Operator voice
  • AWS

Tell us what you need built.

A short note on the device, the user, and the deadline is enough to start.

Start a project