AI voice generator for text to speech, voice cloning, and voice design
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
Not given
Not given
Pricing model
Freemium
Freemium
Pricing
Not given
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
300+ public voice styles and directions to audition
Text to speech with up to 1,000 characters per conversion
Authorized private voice cloning from your own recordings
AI voice design to create original synthetic speakers
Multilingual support: English, Chinese, Japanese, Korean
Generation history and downloadable audio files
Punctuation and phrasing control for delivery direction
Account-bound private voice models
24/7 browser-based generation
Editable audio with revision support
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
Keep audio editable and revisable as scripts change
Unified credit system across all voice tools
Account-bound private models distinguish approved voices from experiments
Treat permission as core to voice cloning workflow
Designed for quick auditions of demanding sentences from real projects
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
Eleven AI
GridBulk