| What it does | AI voices that take direction
| Open-source SDXL-based AI model for native high-resolution anime art generation
|
|---|
| Stage | Startup
| Not given
|
|---|
| Founded | 2025
| Not given
|
|---|
| Based in | US
| Not given
|
|---|
| Pricing model | Freemium
| Open source
|
|---|
| Pricing | Free: 60 points (~1 minute of audio), 1 voice clone, 1 saved voice design. Lite: $9/month with 3,000 points (~50 minutes), 1 saved clone, unlimited cloning. Pro: $24/month with 12,000 points (~200 minutes), 10 saved clones, API & MCP access. Max: $299/month with 150,000 points (~2,500 minutes), 5 te
| Free for personal and research use; prohibits closed-source proprietary monetization
|
|---|
| Key features | - 260+ realistic voices in 200+ languages
- Voice steering: direct how lines are delivered with natural language instructions
- Voice design: describe a voice and get it in seconds
- Karaoke-style word-level highlighting in SRT captions
- MP3 and WAV export
- Sound tags: laugh, sigh, breathe, clear throat
- Multi-voice ebook-to-audiobook conversion
- Two-host podcast creation
- Video dubbing into different languages
| - Native 1536x1536 high-resolution generation without upscaling
- Hybrid Prompting System combining natural English and Danbooru tags
- Stable text encoder fine-tuning for superior concept understanding
- Trained on comprehensive Danbooru2023 dataset
- Full compatibility with ComfyUI, Automatic1111, Forge, and Draw Things
- Superior anatomy rendering with flawless hands and character details
- V-Prediction architecture for enhanced dynamic range and contrast
- Highly flexible base canvas for LoRA training and custom checkpoints
|
|---|
| What makes it different | - Voice steering: direct each line's delivery in plain English without re-recording
- Bootstrapped and independent: no venture funding, answers to users not investors
- Consent-based voice cloning with clear commercial-use terms
- Organic growth through search: no ad spend, thousands discover via Google monthly
- Full commercial-use license on all paid plans for videos, ads, apps and audiobooks
| - Only open-source SDXL model natively trained at 1536x1536 resolution
- Stylistically neutral untuned base canvas unlike Pony Diffusion
- Continuous rapid iterations from v0.1 to v3.5 with aggressive optimization
- Thousands of compatible community-trained LoRAs and derivatives
|
|---|
| Free plan | Not given
| Not given
|
|---|
| Open source | Not given
| Not given
|
|---|
| Platforms | Not given
| Not given
|
|---|
| Public API | Not given
| Not given
|
| Community votes | 0 | 0 |
| DR (Domain Rating by Ahrefs) | 23 ▲ +1 (up) since last check | 13 ▼ −1 (down) since last check |
| Trust Flow (Majestic) | 12 | 5 |
| Citation Flow (Majestic) | 30 | 19 |
| Referring domains (Majestic) | 125 | 45 |