| What it does | Efficient AI text-to-speech model with 82M parameters delivering natural-sounding voice synthesis
| Convert video clips into per-frame depth map videos with AI estimation
|
|---|
| Stage | Not given
| Startup
|
|---|
| Founded | Not given
| 2026
|
|---|
| Based in | SG
| Not given
|
|---|
| Pricing model | Open source
| Freemium
|
|---|
| Pricing | Free to use. Free Chrome Extension with 10,000 characters free every month.
| Credits consumed per second of input video: VDA-Small 2 credits/second, VDA-Base 3 credits/second, VDA-Large 4 credits/second, with a 2-credit minimum. Subscription plans available: Basic $6.90/month with 100 credits, Pro $13.90/month with 250 credits, Max $34.90/month with 750 credits, Pro Max $59.
|
|---|
| 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
| - Three model tiers: VDA-Small for quick previews, VDA-Base for balanced speed and detail, VDA-Large for finest detail
- Grayscale and Turbo visualization modes
- Upload formats: MP4, MOV, WebM, M4V, GIF up to 60 seconds and 200MB
- Per-frame temporal stability with frame-by-frame alignment
- Depth output as MP4 ready for compositing software
- No per-frame rotoscoping required
- Real-time duration verification for accurate pricing
- Relative depth output, not calibrated physical distance
- Support for depth-driven visual effects like fog, defocus, and parallax
|
|---|
| 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
| - Temporally stable depth passes without depth cameras or rotoscoping
- Three model tiers with transparent per-second credit pricing
- Instant price confirmation before processing any video
- Dual visualization modes for different use cases
- Works with everyday video formats and up to 60-second clips
|
|---|
| 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 | 30 ▲ +1 (up) since last check |
| Trust Flow (Majestic) | 10 | 11 |
| Citation Flow (Majestic) | 22 | 33 |
| Referring domains (Majestic) | 154 | 171 |