Efficient AI text-to-speech model with 82M parameters delivering natural-sounding voice synthesis
AI app for UGC-style videos and slideshows on TikTok and Instagram
Stage
Not given
Not given
Founded
Not given
Not given
Based in
SG
CH
Pricing model
Open source
Freemium
Pricing
Free to use. Free Chrome Extension with 10,000 characters free every month.
Free credits for new accounts (100 credits with sign-up). Pro: $39/month ($19 first month) with 1,000 credits/month. Growth: $89/month ($39 first month) with 2,000 credits/month. Agency: $199/month ($79 first month) with 4,500 credits/month. A video costs 20 credits and an image costs 1 credit.
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
Generate AI videos from text descriptions
Generate photo slideshows as carousels
Post to TikTok, Instagram and YouTube
Connect AI agents via MCP
Batch generate multiple video variations
Library of pre-made viral formats
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
Make a month of content in one sitting from a single format
User retains full control over what gets posted and when
Works with apps, e-commerce stores and custom products