Real-time voice translation for Google Meet and Microsoft Teams
High-fidelity photorealistic AI image generation with natural prompting
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Free trial
Open source
Pricing
Free trial: 5 minutes (no card required). After adding a card: up to 30 minutes total free. Paid: US$10 for approximately 65 minutes, US$30 for approximately 205 minutes, US$50 for approximately 390 minutes.
Free and open source
Key features
Real-time voice translation in 19 languages
Live subtitles for both speakers
No installation required for other participants
Works with Google Meet and Microsoft Teams
Automatic language detection for incoming speech
Translation latency of approximately one second
No meeting recording or storage
Works with any Google account
Any language pair translation
Optional auto top-up for uninterrupted meetings
High-fidelity skin and eye rendering with fine pores and light reflections
Robust composition coherence for multi-subject scenes and action shots
Baked-in VAE with optimized color tuning
Simple natural language prompting without complex templates
Compatible with ComfyUI, Automatic1111, and Forge
Works with popular SDXL ControlNets and IP-Adapters
Thousands of compatible LoRAs available
Optimized CFG sensitivity for high quality at lower scales
Natural light scattering and structural accuracy
Experimental Catalyst branch for continuous model evolution
What makes it different
Supports any pair of 19 languages, not limited to English pairs
No installation or setup required for meeting participants
Works with free Gmail accounts without requiring paid plans
Two-way real-time voice translation with live subtitles
Private by design with no audio recording or storage
Minimal prompting complexity with natural language descriptions instead of complex embeddings
Eliminates artificial AI textures and generic rendering artifacts
Open-source with commercial use permissions
Seamless integration into existing AI image generation workflows
Continuously refined through community feedback and experimental development
SottMeet
CyberRealistic XL