Efficient AI text-to-speech model with 82M parameters delivering natural-sounding voice synthesis
AI video studio for creating professional videos with Google DeepMind's Veo 3.1
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 tier: 3 initial credits plus 1 daily credit. Paid plans: Starter $9.9/month (60 credits), Pro $23.9/month (150 credits), Studio $39.9/month (270 credits). One-time top-up: $9.9 for 60 credits valid 30 days. All plans include monthly or yearly payment options and commercial use rights.
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
First & Last Frame Control - define scene start and end points with frame uploads
Multi-Image Reference - match color palette, lighting, and composition across videos
Native audio generation with dialogue, ambient sounds, and music
Scene-level creative control with camera directions
Fast Mode for 30-second previews and Standard Mode for full 1080p quality
Video extension up to 148 seconds by chaining clips
Built-in prompt library with example outputs
Aspect ratio support for 16:9 landscape and 9:16 vertical formats
Private processing with optional watermarking
Video generation history and saved prompts management
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
Transparent pricing with clear per-generation costs shown before rendering
Three modes in unified interface without interrupting creative workflow
First & Last Frame Control feature not available on other platforms
Support for Veo 4 on day one of release with priority access for users
Kokoro TTS
Voe Ai