Amazon Polly Review, Pricing & Alternatives (2026)

Amazon Polly launched at AWS re:Invent in November 2016 and is one of the oldest cloud text-to-speech services still in active development. It sits alongside Amazon Transcribe and Amazon Lex in the AWS AI services group, and it powers voices in Alexa features, Amazon Connect contact centers and thousands of third-party apps. Polly has no studio or editor of its own. You call it from the AWS console, the command line, an SDK or another AWS service such as Lambda, and it returns an MP3, OGG or PCM audio stream. Because it is part of AWS, it inherits the platform's compliance coverage, regional data residency, IAM permissions and consolidated billing. That makes it a default choice for teams whose infrastructure already runs on AWS and who want speech without adding another vendor.

A request sends plain text or SSML, a voice ID, an engine and an output format. SSML tags control pauses, emphasis, pronunciation, speaking rate and pitch, and Polly adds its own tags for breathing sounds and a newscaster speaking style on some neural voices. Lexicons let you define how brand names or acronyms should be pronounced across every request. Speech Marks return timing metadata for each word, sentence or viseme, which apps use to highlight text in sync with audio or drive an avatar's lip movements. For long content, asynchronous synthesis tasks write the output to an S3 bucket instead of streaming it. Audio can be cached and replayed at no extra charge, which keeps costs down for apps that repeat the same prompts.

Polly offers four engines. Standard voices use concatenative synthesis and sound dated but cost the least. Neural voices, added in 2019, use a neural network for more natural prosody and are the common default. Long-form voices, launched in 2023, are tuned for articles and audiobooks where listeners notice monotony over minutes. Generative voices, introduced in 2024, run on a large speech model AWS describes as the most expressive and conversational, and they suit chatbots and voice assistants. Across engines Polly covers roughly 40 languages and variants and more than 100 voices, though generative and long-form voices exist only for a subset of languages. Brand Voice, a custom neural voice built with the AWS team, is available by engagement for companies that want a unique narrator.

Billing is per character processed, with no subscription. Standard voices cost $4 per million characters, neural $16, generative $30 and long-form $100, according to the pricing page; GovCloud rates are about 20% higher. AWS's example: a typical 6,500-character news article costs about three cents with neural voices and 65 cents with long-form. The always-free allowance gives 5 million standard characters a month. Neural, long-form and generative voices get 1 million, 500,000 and 100,000 free characters a month for the first 12 months. Since July 2025 new AWS accounts also receive up to $200 in Free Tier credits that apply to Polly. Costs climb mainly with the long-form engine, which is six times the neural rate, and with Speech Marks, which are billed as additional characters.

Polly's weakness is voice quality at the top end. Its generative voices are good, but independent rankings such as the Artificial Analysis TTS leaderboard place ElevenLabs, Cartesia and newer models ahead on naturalness, and Polly has no instant voice cloning. Google Cloud Text-to-Speech offers more languages and Chirp 3 HD voices at similar prices, while Azure AI Speech has the largest neural voice catalogue and a custom neural voice program. For a developer already on AWS, Polly's strengths are the 5 million free standard characters, IAM-based security, S3 output and predictable per-character billing with no seats or plans. Choose Polly for IVR prompts, accessibility features, notifications and high-volume narration inside AWS. Choose ElevenLabs or Cartesia when the voice itself is the product.