| Overview |
Amazon's automatic speech recognition service for converting audio to text with custom vocabulary and medical transcription support. |
High-speed inference platform optimized for serving open-source models with extremely low latency and high throughput. |
| Pricing |
Pay-per-use ($-$$) |
Pay-per-use ($-$$$) |
| Key Features |
- Real-time streaming
- Batch processing
- Custom vocabulary
- Medical transcription
- Toxicity detection
- Subtitles
|
- Fast inference
- Function calling
- JSON mode
- Grammar mode
- Fine-tuning
- OpenAI-compatible
- Firefunction
|
| Pros |
- Good accuracy
- Medical specialty
- AWS integration
- Custom vocabulary
|
- Very fast inference
- Competitive pricing
- Structured output
- Good function calling
|
| Cons |
- AWS dependency
- Complex pricing
- Region limitations
- Setup overhead
|
- Smaller ecosystem
- Limited model selection
- Newer platform
|
