What it does
AWS text-to-speech for applications, narration and accessibility workflows. It can convert text into speech using supported voice engines, control pronunciation and delivery with SSML, and integrate speech synthesis with AWS applications. Use it to create or improve narration and audio for an authorized creative or application project.
Features
- 01
Convert text into speech using supported voice engines
- 02
Control pronunciation and delivery with SSML
- 03
Integrate speech synthesis with AWS applications
Who it is for
- Create or improve narration and audio for an authorized creative or application project.
These scenarios and steps are editorial guidance based on the official product scope, not independent hands-on results.
Plans, quotas & access
Reference plan：Standard voice / USD 4 per million chars
How to read these conditions
A reference plan, not a complete price comparison. API billing, region, taxes and annual payment may differ. Official documentation review does not confirm a hands-on card or checkout test.
Pricing model
Usage basedOfficial source reviewed · 2026-10-21View evidence · Pricing model
Outside applicable free allowances: Standard USD 4, Neural USD 16, Generative USD 30 per million characters. AWS free eligibility depends on account date and plan.
Official source Review due：2027-01-19Plan price
Usage based · see official plansNot verifiedView evidence · Plan price
The official page does not provide enough evidence for this condition.
Free access and quota
Limited free trialOfficial source reviewed · 2026-10-21View evidence · Free access and quota
Outside applicable free allowances: Standard USD 4, Neural USD 16, Generative USD 30 per million characters. AWS free eligibility depends on account date and plan.
Official source Review due：2027-01-19Official API
UnknownNot verifiedView evidence · Official API
The official page does not provide enough evidence for this condition.
Card for free / trial
UnknownNot verifiedView evidence · Card for free / trial
The official page does not provide enough evidence for this condition.
Free quota & limits
适用免费额度之外，标准音色 4 美元、神经音色 16 美元、生成式音色 30 美元/百万字符；免费资格取决于开户日期和账户方案。 / Outside applicable free allowances: Standard USD 4, Neural USD 16, Generative USD 30 per million characters. AWS free eligibility depends on account date and plan.
Getting started
Use a short text or audio sample, select the relevant voice or processing setting, then listen before export.
These scenarios and steps are editorial guidance based on the official product scope, not independent hands-on results.
What to watch out for
- Check voice consent, recording rights and music licenses; listen for synthesis and processing artifacts.
- Price checked 2026-10-21: Outside applicable free allowances: Standard USD 4, Neural USD 16, Generative USD 30 per million characters. AWS free eligibility depends on account date and plan.
Evidence & updates
Official product information was reviewed. ToolAha has not claimed an independent hands-on test.
Profile reviewed: 2026-10-21 · Version 3
This entry uses the official publisher or maintainer identity; it does not imply a standalone product icon for this resource. Official source
