Minimum system requirements: Intel i7, 16G RAM, NVIDIA GeForce GTX1060 Ti – Model used: Small
NVIDIA GeForce RTX 4060Ti – Model used: Medium
NOTE: Install CUDA for better performance (Windows only)
Tested with: Apple Mac Book Pro M2 and M3 chips.
Total Number of Cores: 12
(8 performance and 4 efficiency)
Memory: 16 GB
Total Number of GPU Cores: 19 (Metal 3)
Models in use: All models
VOX Screen Realtime Speech-to-Screen.
Offline app solution for displaying on screen and stream live speech transcription and translation.
AI generated realtime Speech-to-Text live transcription and translation Content Display Solution.
Software designed by events professionals for live captions and translation display for live events, education and government use.
High-performance realtime “Speech to Text” (STT) App build on OpenAI’s automatic speech recognition (ASR) models.
// Software application developed by: Web Video Streaming LTD using Open AI Whisper Models.
References: https://openai.com/index/whisper/
Credits to the following developers whose work has contributed to building current app.
whisper.cpp – https://github.com/ggerganov/whisper.cpp (MIT License)
Realtime processing and UI implementations credits to: https://github.com/chidiwilliams/buzz (MIT License)
Developer agency credits: Dev Soft UK Limited
VOX SCREEN.
All rights reserved 2024 (C) London, UK.
Contact us
VOX SCREEN
T/U Web Video Streaming LTD.
