| What it does | Efficient AI text-to-speech model with 82M parameters delivering natural-sounding voice synthesis
| Multimodal AI foundation model for video, image, and audio generation
|
|---|
| Stage | Not given
| MVP
|
|---|
| 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.
| Basic: $14.95/month or $179.4/year (60,000 credits, approximately 1,200 images or 400 videos); Plus: $29.95/month or $359.4/year (144,000 credits, approximately 2,880 images or 960 videos); Pro: $49.95/month or $599.4/year (264,000 credits, approximately 5,280 images or 1,760 videos). All plans incl
|
|---|
| 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
| - Video generation with native audio up to 20 seconds
- Text-to-video, image-to-video, and video-to-video reference transfer
- Multilingual dialogue and sound design
- Image synthesis and editing in multiple styles
- Agentic multi-shot chaining for longer sequences
- Action prediction for physical AI and robotics
- Style diversity and typography generation
- Reference-based video generation for consistent characters
- Multilingual text rendering in images
|
|---|
| 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
| - Unified multimodal architecture learning from images, videos, and audio simultaneously
- Native audio generation synchronized with video
- Self-Flow architecture for improved quality and task performance
- Multi-shot chaining for extended narratives with consistent characters
- Integrated action prediction for robotics and physical AI
|
|---|
| 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) | 36 ● no change since last check | 4 ▲ +4 (up) since last check |
|---|
| Trust Flow (Majestic) | 10 | 3 |
|---|
| Citation Flow (Majestic) | 22 | 18 |
|---|
| Referring domains (Majestic) | 154 | 21 |
|---|
Kokoro TTS
Flux 3