Amazon Polly price per 1M characters, and a 5,000-character script
Polly lists Standard at $4, Neural at $16, Generative at $30 and Long-form at $100 per 1M characters. A 5,000-character script next to Sume TTS 1.0.

Amazon Polly lists four voice engines per 1 million characters: Standard $4, Neural $16, Generative $30 and Long-form $100. A 5,000-character script costs $0.0200, $0.0800, $0.1500 and $0.5000 on those engines. Sume TTS 1.0 is $0.0475 per 1,000 characters, which is $0.2375 for the same script.
Polly's prices are from its pricing page, read 2026-10-01; Sume's from the rate card. The conversion is characters divided by 1,000,000 times the per-million price.
What does a 5,000-character script cost on each engine?
Same script length, same arithmetic. The page quotes the standard US region; it separately lists higher GovCloud prices for Standard and Neural.
| Engine | As listed | 5,000 characters |
|---|---|---|
| Polly Standard | $4.00 per 1M characters | $0.0200 |
| Polly Neural | $16.00 per 1M characters | $0.0800 |
| Polly Generative | $30 per 1M characters | $0.1500 |
| Polly Long-form | $100.00 per 1M characters | $0.5000 |
| Sume TTS 1.0 | $0.0475 per 1,000 characters | $0.2375 |
Does Polly have a free tier I should count?
Yes. The page lists 5 million Standard characters per month, and for the first 12 months 1 million Neural, 500 thousand Long-form and 100 thousand Generative characters per month. A small project can sit entirely inside those numbers, so compare at your real monthly volume, not at one script.
What is the Sume number based on?
Sume TTS 1.0 counts the transcript's characters, spaces and punctuation included, up to 20,000 per request. The quote assumes an estimated 1,000 characters when you do not pass a size. See TTS API pricing for how reservation works.
Is the cheapest engine the right comparison?
Not by price alone. Polly's Standard engine is the cheapest line, but the page does not describe voice quality, so a price table cannot tell you which engine sounds right for narration. Listen to a sample of your own text on each, then compare cost. Sume TTS 1.0 has no engine picker; the API reference says model and model_id are rejected with a 400.
Sources
Related posts
More in Pricing
- Anam custom avatar slots per plan vs Sume avatar handles
Anam limits active custom avatars by plan, from 1 on Free to 10 on Professional. Sume's avatar docs describe a handle per avatar and one avatar per video.
- Anam per-second billing and spend cap vs Sume reserve at submit
Anam bills live sessions by the second against a spend cap. Sume reserves the estimated USD at submit, captures it on success and refunds it on failure.
- Anam session limit per plan vs Sume's 4-60 second window
Anam caps one live session by plan, from 3 minutes on Free to 2 hours on Growth. Sume limits each avatar request to a 4-60 second estimated script.
- Arcads MCP out of credits vs Sume 402 insufficient_credits
Arcads says generation fails without credits. Sume answers 402 insufficient_credits before provider work, and an MCP agent can preview cost with dry_run first.
Written by Sume