| Overview |
AWS text-to-speech service offering lifelike speech synthesis with neural and standard voices in dozens of languages. |
AI-powered search and answer API that combines LLMs with real-time web search for grounded, cited responses. |
| Pricing |
Pay-per-use ($-$$) |
Pay-per-use ($$-$$$) |
| Key Features |
- Neural voices
- Standard voices
- 30+ languages
- SSML
- Lexicons
- Speech marks
- Newscaster style
|
- Online models
- Real-time search
- Citations
- Sonar models
- Grounded answers
|
| Pros |
- Low cost
- Reliable
- Many languages
- AWS integration
|
- Real-time information
- Built-in citations
- Grounded responses
- Simple API
|
| Cons |
- Less natural than competitors
- Limited voice styles
- AWS dependency
|
- Higher cost
- Limited customization
- Search-focused only
|
