Efficient AI text-to-speech model with 82M parameters delivering natural-sounding voice synthesis
AI batch image generation with grid splitting: one prompt, up to 16 images, one credit
Stage
Not given
Startup
Founded
Not given
2026
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 plan includes 20 credits on signup with the first generation free. Basic: $19/month for 2,000 credits/month (≈32,000 images with 4×4 grid). Pro: $49/month for 5,000 credits/month (≈80,000 images with 4×4 grid). Max: $99/month for 10,000 credits/month (≈160,000 images with 4×4 grid).
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 up to 16 images in a single 4×4 grid
Grid splitting into individual pixel-perfect assets
REST API with sync and async endpoints
MCP server for AI agent integration
Reference image support for style guidance
Runs on Google Gemini and OpenAI GPT Image models
Dashboard history with searchable generations
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
One credit per grid instead of per image, reducing cost per image to 1/16 for 4×4 grids
Contact-sheet view for side-by-side comparison of all results
API and MCP server built for AI agents as first-class users
Independent and self-funded operation
First generation completely free with 20 signup credits
Kokoro TTS
GridBulk