Efficient AI text-to-speech model with 82M parameters delivering natural-sounding voice synthesis
AI scientific figure generator for journal-ready research illustrations
Stage
Not given
Not given
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 account with 100 starting credits and 10 daily check-in credits (valid 30 days). Starter plan: $84/year or $108/month for 1,000 monthly credits. Pro plan: $180/year or $228/month for 3,000 monthly credits. Lab plan: $468/year or $588/month for 10,000 monthly credits. One-time credit packs avail
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 figures from text descriptions, sketches or abstracts
Editable text labels and vector arrows on canvas
Accuracy checks comparing labels to original plan
Journal-ready exports at 300 or 600 dpi
Multiple export formats: PNG, JPG, SVG, PPTX
Pre-planned layout review before generation
Publication license certificates with online verification
Journal color palettes from Nature, Science, Cell and others
Free PRISMA flow diagrams and phylogenetic trees
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
Complete workflow from idea to journal-ready export in one tool
Editable after generation instead of regenerating from scratch
Built for peer review standards with accuracy checks
Takes sketch or photo reference to preserve layout intent
Designed for researchers without design budget or skills