Efficient AI text-to-speech model with 82M parameters delivering natural-sounding voice synthesis
AI-powered subtitle and dubbing generator for video and audio content localization
Stage
Not given
Established
Founded
Not given
Not given
Based in
SG
Not given
Pricing model
Open source
Freemium
Pricing
Free to use. Free Chrome Extension with 10,000 characters free every month.
Free trial with 1 hour of video translation credits. Paid plans: Junior $18/month (2 hours credits) or $12/month annually (24 hours credits); Starter $59/month (5 hours credits) or $48/month annually (60 hours credits); Enterprise from $299/month with custom credits. Credits are consumed at differen
Key features
82M parameter efficiency for lightweight, scalable performance
Multilingual support including English, French, Korean, Japanese, and Mandarin
Customizable voice packs with multiple lifelike voice options
Automatic content segmentation for chapter and section detection
OpenAI-compatible API endpoint for easy integration
Real-time audio generation with NVIDIA GPU acceleration
Processes up to 510 tokens in a single pass for longer audio outputs
Chrome extension for reading webpages aloud
Auto-subtitles generation using advanced AI
Translation in over 200 languages
AI voice cloning in 30 languages
Voice isolation to separate dialogue from background audio
Subtitle styling and animation customization
Script to subtitles conversion with synchronization
Burn-in subtitle export and subtitle file formats
Lip-sync technology (Beta)
Advanced online editor for subtitle and dubbing refinement
YouTube channel integration and social media optimization
What makes it different
Outperforms larger models like XTTS (467M params) and MetaVoice (1.2B params) despite having only 82M parameters
Open-source and free for both commercial and personal use under Apache 2.0 license
Lightweight architecture enabling deployment on CPU and GPU with minimal resources
Trained on high-quality, permissively licensed audio for accurate natural-sounding speech
Designed for scalability while preserving excellent audio quality
6 years of development focused specifically on subtitling quality and accuracy
Translation workflow designed specifically for subtitles rather than generic translation
Preserves original audio background and ambient sounds while replacing only vocals
Immediate subtitle generation with optional post-editing for rapid deployment
Kokoro TTS