Text-to-image diffusion model for generating high-quality non-photorealistic images
Automatic speech recognition, speech-to-text transcription and translation for files and live audio
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
GB
Pricing model
Open source
Freemium
Pricing
Not given
Pay as you go: $0.20 per hour for files, $0.60 per hour for live transcriptions, with $5 free signup credit. Premium: $20 per month (billed annually) or $25 per month (monthly), including $25 monthly credit. Enterprise: custom pricing with volume rates and dedicated capacity.
Key features
Text-to-image generation based on textual descriptions
Fine-tuned on approximately 80,000 pony images
User-friendly interface for easy image generation
CLIP-based aesthetic ranking for quality evaluation
Quality scoring mechanism with score tags
CreativeML OpenRAIL license for free use and redistribution
Community engagement and collaborative development
Speaker recognition and labeling by name
Automatic translation into up to 100 languages
Real-time live transcription with live corrections visible to all listeners
Voice cloning from 30 seconds of audio
Reference script and slides for improved accuracy on names and terms
Broadcast with password protection and public or private sharing
Automatic summaries generated in every language
Search transcripts by exact wording or by meaning across any language
What makes it different
Specialized for non-photorealistic art and creative styles
Fine-tuned specifically on pony-themed artwork
Open source with commercial use permitted
Listeners pay nothing; only audio transcribed is charged, same price in app or API
Translation read aloud in the original speaker's cloned voice, not generic robot voice
Server-side accuracy with context checking, reference scripts and live corrections
Works with any audio source: microphone, file upload, URL, YouTube live, radio, RTMP encoder
No app or sign-up required for listeners; they open a link or scan QR code in browser