| Overview |
Amazon's automatic speech recognition service for converting audio to text with custom vocabulary and medical transcription support. |
End-to-end computer vision platform for building, training, and deploying custom object detection and classification models. |
| Pricing |
Pay-per-use ($-$$) |
Freemium ($-$$$) |
| Key Features |
- Real-time streaming
- Batch processing
- Custom vocabulary
- Medical transcription
- Toxicity detection
- Subtitles
|
- Dataset management
- Auto-labeling
- Model training
- Deployment
- Inference
- Active learning
- Universe dataset hub
|
| Pros |
- Good accuracy
- Medical specialty
- AWS integration
- Custom vocabulary
|
- Easy to use
- End-to-end platform
- Active learning
- Large community
|
| Cons |
- AWS dependency
- Complex pricing
- Region limitations
- Setup overhead
|
- Limited free tier
- Custom models only
- Can be expensive at scale
|
