Arkinu
AWS service comparison

Amazon Lex vs Amazon Polly: differences and when to use each

Amazon Lex
Amazon Polly

Often confused on the examQuestions tend to offer one as a distractor for the other: look for the phrase in the scenario that tips the balance.

Machine Learning

Amazon Lex

On the radar· Amazon Lex V1 is no longer supported

Service for building conversational interfaces (chatbots) using voice and text. It combines speech recognition and natural language understanding to recognize the user's intent and fulfill it, for example by invoking an AWS Lambda function.

Exam phrases that point here

  • «build a voice or text chatbot with a conversational interface»

    Amazon Lex is used to build bots that understand what the user says or types and hold a conversation to complete a task.

    When not: If you only need to convert text to speech, the answer is Amazon Polly; if you only need to convert audio to text, Amazon Transcribe. Lex is for dialogue, not for a standalone conversion.

  • «recognize the user's intent and ask for the missing information»

    In Lex, each action is an intent that is triggered by sample utterances, and the required data are slots that the bot asks for with prompts over several turns.

    When not: If there is no conversation and you only want to classify a text (sentiment, entities), Amazon Comprehend is the fit.

  • «a contact center with interactive voice response that understands natural language»

    Lex bots integrate into Amazon Connect Customer (formerly Amazon Connect) flows: the customer says or presses what they need, and the bot interprets it to resolve it or route the call.

    When not: The contact center itself is Amazon Connect Customer; Lex provides the bot. If the requirement is to analyze calls that have already been recorded (sentiment, issues), think of Amazon Transcribe Call Analytics.

  • «run business logic when the conversation completes»

    Lex invokes an AWS Lambda function to validate what the user says and to fulfill the request, for example saving a reservation.

    When not: Lex can also return the intent and slots to the client so that the application does the work. And if the process has many steps with waits and retries, orchestration usually belongs in AWS Step Functions.

  • «publish the same bot on Slack, Facebook Messenger, or SMS»

    A Lex bot can be published on messaging services and in mobile apps.

    When not: For Alexa devices you need an Alexa skill. Exporting the bot schema to a skill was a Lex V1 feature, which stopped being supported on September 15, 2025.

Often paired with

  • AWS Lambda
Study Amazon Lex →

Machine Learning

Amazon Polly

Service that turns text into lifelike speech (text-to-speech). It is used to build applications that talk, in multiple languages and with different voices, for example for news readers or accessibility.

Exam phrases that point here

  • «convert text into natural-sounding speech»

    Amazon Polly takes text and returns spoken audio with lifelike voices, ready to play or store.

    When not: If the direction is the opposite, from audio to text, the answer is Amazon Transcribe. If you also need to hold a conversation with the user, think of Amazon Lex, which together with Polly forms complete voice interfaces.

  • «control the pronunciation, pauses, or speed of the voice»

    With SSML you mark pauses, emphasis, speed, pitch, and volume, and with custom lexicons you set how specific words are pronounced.

    When not: If the problem is that the system does not recognize certain words correctly in an audio recording, that is speech recognition: it is solved with Amazon Transcribe custom vocabulary.

  • «generate audio files from long texts and store them for reuse»

    Polly asynchronous synthesis processes long texts in the background and places the audio in an Amazon S3 bucket; the generated audio can be played as many times as you want.

    When not: For short sentences that must play almost instantly, use regular synthesis (SynthesizeSpeech), which returns the audio in the response.

  • «highlight each word on screen while the text is read aloud»

    Polly speech marks return the timing of each sentence, word, or viseme (mouth shape), to synchronize highlighted text or animations with the audio.

    When not: Polly does not translate: if the text must be read in another language, it is first translated with Amazon Translate and then synthesized.

  • «read content aloud to improve accessibility»

    Helping people with visual impairments or reading difficulties is one of the typical uses AWS cites for Polly.

    When not: If the content is in an image or a scanned document, the text must first be extracted (Amazon Textract for documents) and then synthesized.

Study Amazon Polly →