Open-source AI video generator for text, image, and audio to video creation
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
Freemium
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-video generation from natural language prompts
Image-to-video transformation with dynamic motion and animation
Audio-to-video synchronization with tight lip-sync
Native portrait video at 1080x1920 resolution
22 billion parameter Diffusion Transformer engine
4x-expanded text connector for accurate prompt interpretation
Face and character preservation across frames
Multi-modal generation pipeline with depth conditioning
Rebuilt VAE for sharper output and better texture preservation
Video output up to 1080p in multiple aspect ratios
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
18x faster throughput than competing open-source models on H100 GPUs
Cloud-based rendering with no local GPU or installation required
Free credits for new accounts with no signup friction
Full commercial rights with no watermarks or royalty fees
Open-source model weights available on Hugging Face for local use
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