| Overview |
Amazon's automatic speech recognition service for converting audio to text with custom vocabulary and medical transcription support. |
AI voice generator API for creating studio-quality voiceovers with natural-sounding synthetic voices. |
| Pricing |
Pay-per-use ($-$$) |
Subscription ($-$$$) |
| Key Features |
- Real-time streaming
- Batch processing
- Custom vocabulary
- Medical transcription
- Toxicity detection
- Subtitles
|
- 120+ voices
- 20 languages
- Voice cloning
- Emphasis control
- Pitch and speed
- Studio editor
|
| Pros |
- Good accuracy
- Medical specialty
- AWS integration
- Custom vocabulary
|
- Natural sounding
- Easy to use
- Good language support
- Voice customization
|
| Cons |
- AWS dependency
- Complex pricing
- Region limitations
- Setup overhead
|
- Subscription model
- Limited API docs
- Fewer developer tools
|
