Amazon Lex vs Rasa

Amazon Lex lets application builders create conversational interfaces that respond to natural-language voice or chat input. It combines automatic speech recognition for voice with natural language understanding for voice and text interactions. Builders can use a visual flow builder and AI bot generation. The Automated Chatbot Designer analyzes conversation transcripts and proposes an initial design with intents and slot types; Test Workbench supports creating test sets and reviewing results. For FAQ responses, an intent can query an authorized knowledge source and foundation models from Amazon Bedrock. Bots can be deployed on mobile devices and chat services including Facebook Messenger, Slack, Kik, and Twilio SMS. AWS integrations include Lambda for backend logic, Cognito for authentication, Polly for text-to-speech, and Amazon Connect for contact centers. Lex is available for Android, iOS, web, and API use. Text and speech requests use pay-as-you-use pricing, with no upfront commitment or minimum fee in the listed examples. Automated Chatbot Designer training time is listed at $0.50 a month, with pricing described as per minute of training time. The AWS Free Tier is available for six months after account creation, with credits subject to stated eligibility and expiry terms.

Rasa has no write-up on Specifiction yet; its figures are above.