| Overview |
Amazon's automatic speech recognition service for converting audio to text with custom vocabulary and medical transcription support. |
A serverless PostgreSQL database with auto-scaling, branching, and a generous free tier for modern applications. |
| Pricing |
Pay-per-use ($-$$) |
Freemium (Free-$69/month) |
| Key Features |
- Real-time streaming
- Batch processing
- Custom vocabulary
- Medical transcription
- Toxicity detection
- Subtitles
|
- Serverless PostgreSQL
- Auto-scaling
- Database branching
- Point-in-time recovery
- Connection pooling
- Auto-suspend
- Logical replication
- CLI
|
| Pros |
- Good accuracy
- Medical specialty
- AWS integration
- Custom vocabulary
|
- Generous free tier
- True serverless
- Database branching
- PostgreSQL compatible
|
| Cons |
- AWS dependency
- Complex pricing
- Region limitations
- Setup overhead
|
- Newer platform
- Cold starts on free tier
- Limited extensions
- Scaling costs can surprise
|
