Amazon Polly
Fully managed text-to-speech service that turns plain text or SSML into lifelike audio.
Verified against AWS documentation · 2026-08-24
Key facts
- 01Text in (plain or SSML), audio out — MP3, OGG Vorbis, PCM, or JSON speech marks
- 02Four engines behind one API: standard, neural, long-form, generative — quality and price rise in that order
- 03SynthesizeSpeech is real-time, 3,000 billed characters max; StartSpeechSynthesisTask is async, 100,000 characters, writes straight to S3
- 04Lexicons fix pronunciation, SSML controls pauses, pitch and rate — SSML tags are never billed
Exam triggers
Phrases and scenarios that point here.
- "Turn text into lifelike speech", "voice-enable the app", "read the article aloud" → Polly
- Audio → text is the opposite direction → Transcribe, not Polly
- Whole documents or text past the real-time limit → StartSpeechSynthesisTask + S3, with optional SNS on completion
- Brand names or acronyms pronounced wrong → lexicon; needs a pause or slower delivery → SSML
Not this service
- Speech → text (transcripts, call analytics) → Amazon Transcribe
- Working out what a caller wants and driving the conversation → Amazon Lex (Lex speaks using Polly)
Use cases
- 01IVR and contact centre prompts synthesized once and cached in S3 — changing a menu becomes a text edit and a redeploy, not a studio booking
- 02"Listen to this article" audio on a blog or news site, generated at publish time and served from CloudFront alongside the post
- 03E-learning narration on the long-form engine, so a 20-minute module doesn't drift into flat robot delivery halfway through
- 04Speech marks driving word-by-word highlighting or avatar lip-sync in reading and language-learning apps
- 05Voice replies for an LLM chatbot on the generative engine, streaming audio out while the model is still producing tokens
How it's charged
- 01Billed per character of text synthesized — SSML tags don't count toward billed characters
- 02Engine choice is the whole cost story: standard $4, neural $16, generative $30, long-form $100 per 1M characters
- 03Speech marks bill as their own request — asking for audio and marks on the same text charges you twice
- 04Caching and replaying generated audio is free, so pre-synthesizing repeated phrases means you pay once, forever
- 05No charge for lexicons or idle usage; S3 storage and internet data transfer are billed by those services, not Polly
