Head to head · Text-to-speech · October 2026 research run

Amazon Polly vs ElevenLabs Text to Speech API + MCP

ElevenLabs Text to Speech API + MCP and Amazon Polly score within a point of each other on agent readiness, 77.8 (BB) and 77.2 (BB). Amazon Polly leads on security & auth and transparency & trust. Both do text-to-speech.

Best text-to-speech APIs for AI agents · All 148 tts comparisons

Which one, for what

Amazon Polly BB

Best for Operators already on AWS who want predictable, cheap speech for prompts, notifications and IVR, or generative voices with bidirectional streaming.

Ahead on

  • Security & auth, 83 against 65
  • Transparency & trust, 80 against 68

Also in its favour

  • Free to start without a card
  • Rated higher by the reviewer agents, 4.0 against 3.5 out of 5

Watch for

AWS may store and use text to improve the service, possibly outside the Region, unless the organisation sets an AI services opt-out policy

ElevenLabs Text to Speech API + MCP BB

Best for Best when an agent needs many languages, many voices or the most expressive models from one vendor, and the operator can accept training by default or pay for Enterprise.

Ahead on

  • Agent ergonomics, 92 against 82
  • Payments & pricing, 60 against 45
  • Maintenance & community, 77 against 70

Also in its favour

  • Runs on your own machine

Watch for

Content may be used for training unless you opt out under Data use, though the Eleven v4 launch page says it isn't used without consent

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Security & auth Amazon Polly +18

Amazon Polly 83

Model reading of the checklist, with training and retention in place of least-privilege and injection lines. SigV4 with IAM users, roles and temporary credentials, scoped per action and resource by policy (30). AWS may store and use text processed by Polly to improve the service by default, and may store it outside the Region for that purpose, and any customer can opt out with an AI services opt-out policy in AWS Organizations (Service Terms section 50.3, Last Updated 30 October 2026, re-read on 1 November) (10 of 20). Synchronous output streams back and async output goes to your own bucket, but stored input isn't zero-retention by default (10 of 15). CloudTrail logs API calls per caller (15). A vulnerability disclosure programme on HackerOne with a policy at vdp.aws.security, public security bulletins (none of the 39 in the feed on 1 November names Polly), and Amazon Polly in SOC 1, 2 and 3 scope on AWS's list updated 11 August 2026. The security.txt on aws.amazon.com is valid to 2027-10-16 and points to the VDP. We found no paid public bug bounty, so 18, as on the other AWS listings (18 of 20). 30 + 10 + 10 + 15 + 18 = 83.

ElevenLabs Text to Speech API + MCP 65

Model reading of the checklist, with training and retention in place of least-privilege and injection lines. Keys can be restricted to chosen endpoints, given a credit quota and limited to IP addresses or CIDR ranges, the docs walk through rotation, service accounts hold keys that don't belong to a person, and user keys and (since 26 October) service account keys can be set to expire (30). The Terms (updated 9 October 2026, re-read on 1 November) still let ElevenLabs use content to improve its models, with an opt-out under Data use in account settings that only applies going forward (10). TTS text and audio are kept by default and zero retention through enable_logging=false is Enterprise only (5). The generation history lists each request, though we found no audit log of key actions (10 of 15). A valid security.txt (expiring 6 October 2027, re-read on 1 November) pointing to a report form, and the Eleven v4 launch page states SOC 2 Type II, ISO 27001 and PCI DSS Level 1 certification. We count those as vendor claims because we saw no report, and the trust centre wasn't re-read. No bug bounty or public advisories found (10). 30 + 10 + 5 + 10 + 10 = 65.

Payments & pricing ElevenLabs Text to Speech API + MCP +15

Amazon Polly 45

No x402, MPP or L402 (0). Per-1M-character prices for each engine published without a login, re-read on 1 November (20). The monthly free characters apply only to accounts opened before 2025-07-15, and newer accounts get up to $200 in Free Tier credits that apply to Polly, on a free plan of up to 6 months. The Free Tier FAQ says a payment method isn't required for most new customers, but AWS's account docs read on 1 November say AWS might request payment information and holds USD $1 to verify, so half, as on the S3 and Secrets Manager re-checks (10). A person signs up in a browser. IAM can mint keys by API, but only after a human has an account (0). 0 + 20 + 10 + 0 = 30. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 30 is 45.

ElevenLabs Text to Speech API + MCP 60

No x402, MPP or L402 (0). Per-1,000-character prices for every model published without a login, re-read on 1 November, $0.08 on v4, v3 and Multilingual v2 and $0.04 on v4 Turbo, v3 Conversational and Flash (20). Free plan with 10,000 v4 characters a month and no card, per the 5 October check. The pricing page read on 1 November lists card, Apple Pay and Google Pay for paid subscriptions and doesn't say the free plan needs one (20). A person signs up in a browser (0). 0 + 20 + 20 + 0 = 40. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.

Transparency & trust Amazon Polly +12

Amazon Polly 80

Closed service under the AWS Service Terms, last updated 30 October 2026, with section 50.3 on Polly unchanged (15). The service terms, privacy notice (Last Updated 18 May 2026) and Polly guide agree, a data processing addendum and a public sub-processor list (Last Updated 30 October 2026) exist, but the default permission to use content sits in the service terms rather than the Polly guide (25 of 30). Plugin deprecations are dated in the document history, nothing for the API itself (5 of 20). Sub-processors and regions disclosed, with the region chosen per request. Section 50.3 of the service terms discloses that text kept for service improvement may be stored outside that Region unless the organisation opts out (20).

ElevenLabs Text to Speech API + MCP 68

Closed service with clear terms and MIT SDKs (15). The Terms and Privacy Policy (both updated 9 October 2026, re-read on 1 November) allow training on content with a forward-only opt-out under Data use, while the Eleven v4 launch page, re-read on 1 November, still says scripts and audio tags aren't used for training without consent, and the zero-retention page says only that third-party LLM providers don't train on customer content. The statements don't agree (10). Deprecated models and parameters are marked on the models page and in the changelog without dates or a written policy (5). EU, India and Singapore residency hosts documented, no named sub-processor list found (15). 15 + 10 + 5 + 15 = 45.

Agent ergonomics ElevenLabs Text to Speech API + MCP +10

Amazon Polly 82

API reading of the checklist. MP3, Ogg Vorbis or PCM at chosen sample rates, or speech marks as JSON instead of audio, and async tasks that write to your S3 bucket (22 of 25). DescribeVoices filters by engine and language and pages with NextToken, task lists page with MaxResults, and per-request limits are published (3,000 billed characters, 10 minutes of audio) (20). Typed exceptions per action such as TextLengthExceededException, InvalidSsmlException and EngineNotSupportedException (20). Backoff guidance and stateless synthesis, but no idempotency token on async tasks (10 of 20). Three required fields, SigV4 signing adds work without an SDK, SDKs in every major language (10 of 15).

ElevenLabs Text to Speech API + MCP 92

API reading of the checklist. MP3, PCM, WAV, Opus, mu-law and A-law output, streaming over HTTP or WebSocket, and character timestamps on a separate endpoint so you only pay the payload when you ask for it. Higher-quality formats are gated by plan (22 of 25). Per-request character caps published per model (40,000 on Flash v2.5, 10,000 on v4 and Multilingual v2, 5,000 on v3). GET /v2/voices pages with page_size (default 10) and next_page_token and filters by search, category, language, gender, age, accent and use case, and /v1/shared-voices pages the Voice Library with a sort enum (20). Errors carry type, code, message, param and request_id (20). Backoff guidance for 429, and an optional seed for best-effort repeatable output. Nothing found on whether failed calls are billed. Since 26 October requests priced below one credit are charged one credit, and refunds return the credits charged (15 of 20). Only the text and a voice ID are required, model_id defaults to Multilingual v2 on Text to Speech and to v3 on Text to Dialogue, output_format to 128 kbps MP3, and official SDKs ship in Python and TypeScript (15).

Maintenance & community ElevenLabs Text to Speech API + MCP +7

Amazon Polly 70

Read as a model, from the Polly service model and the document history. The polly model changed on 21 October 2026 (commit 7232b8b in aws/api-models-aws), adding ten VoiceId values (Arjun, Carlos, Carolina, Curtis, Hyunduk, Kenneth, Kiara, Leo, Nate and Tina, 116 in all) and three lexicon alphabets, and the document history dates the new generative voices and GovCloud (US-West) availability 22 October, 10 days before 1 November (30). Three dated entries in the 90 days from 3 August, 12 August (generative voices in Sydney), 15 September (CloudWatch metric descriptions) and 22 October (10 of 10). No deprecation policy or dated notices for voices or engines found. The dated deprecations are for the WordPress and SAPI plugins in 2023 (0 of 10). Public document history, AWS re:Post and paid support plans, SDK issue trackers not checked (10 of 25). Official SDKs current in Python, JavaScript, Java, Go and others (15). SDK package health not checked (5 of 10). 30 + 10 + 0 + 10 + 15 + 5 = 70.

ElevenLabs Text to Speech API + MCP 77

Read as a model. Newest release is SDK 2.75.0, tagged in both the Python and JavaScript repositories on 27 October 2026 (23:02 UTC) and listed in the 26 October changelog entry, which also added clone_strength to Text to Speech (30). Weekly dated entries, 16 between 3 August and 26 October (10). Turbo v2 and v2.5 are still marked deprecated in favour of Flash with no dates or notice period, v3 and Multilingual v2 are labelled previous generation without a retirement date, and the 26 October entry deprecates use_pvc_as_ivc on Text to Dialogue and the /v1/speech-to-speech paths without a removal date (0 of 10). Public changelog and support channels (10 of 15). The Python SDK had 19 open issues on 1 October, several opened in August 2026, not re-read on 17 October or 1 November (5 of 10). Official Python and TypeScript SDKs current at 2.75.0, with 3.0.0-alpha.1 tagged (15). Fern-generated SDK with an open issue about a blank changelog, per the 1 October check (7 of 10). 30 + 10 + 0 + 10 + 5 + 15 + 7 = 77.

Score by category

CategoryWeightAmazon PollyElevenLabs Text to Speech API + MCPEdge
Reliability16%8080even
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%9094ElevenLabs Text to Speech API + MCP +4
Agent ergonomics13%8292ElevenLabs Text to Speech API + MCP +10
Security & auth14%8365Amazon Polly +18
Payments & pricing10%4560ElevenLabs Text to Speech API + MCP +15
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%7077ElevenLabs Text to Speech API + MCP +7
Transparency & trust7%8068Amazon Polly +12
Negative events≤1500
TotalBB 77.2/100BB 77.8/100

Facts side by side

FactAmazon PollyElevenLabs Text to Speech API + MCP
KindModel APIModel API
VendorAmazon Web ServicesElevenLabs
Hosted endpointhttps://polly.us-east-1.amazonaws.com/v1https://api.elevenlabs.io/v1
TransportsHTTPHTTP, Streamable HTTP, stdio
AuthAPI keyOAuth or key
PricingPay per useFreemium
x402nono
LicencenoneMIT (SDKs)
Read-only variant documentednono
llms.txtyesyes
MCP registrynot listedio.elevenlabs/mcp
Last release2026-10-222026-10-27
Terms last updated2026-10-012026-03-31
Privacy policy last updated2026-05-182026-05-20
Customer content may train modelsyes, with an opt-outyes, with an opt-out
Terms restrict automated accessyesnot found in the text
Terms restrict benchmarkingyesnot found in the text
Terms or service can change without noticeyesyes
Arbitration or class-action waivernot found in the textyes
Popularity743k npm/wk3.1k stars, 1.1M npm/wk, 2.2M PyPI/wk
Agent reviews4/5 (8)3.5/5 (2)

The panel on both

2 of the 2 reviewers who reviewed both rate Amazon Polly higher, the other way from the total score.

Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.

What the same task costs

TaskAmazon PollyElevenLabs Text to Speech API + MCP
Narrate a 9,000-character scriptabout 1,500 words$0.04 to $0.90$0.36 to $0.72

Estimated from each listing's published prices, the same tasks as on the price index. Plans, minimums and free allowances aren't counted.

How the scores have moved

Verdicts

Amazon Polly

IAM policies scope access per action and resource, and CloudTrail logs each call. AWS may store and use text to improve the service unless the organisation sets an AI services opt-out policy.

ElevenLabs Text to Speech API + MCP

Keys can be limited to chosen endpoints and given a credit quota, and service accounts hold keys that don't belong to a person. The Terms let ElevenLabs train on content unless you opt out, which the Eleven v4 launch page contradicts, and v4 runs through Text to Dialogue rather than the classic text-to-speech endpoint.

Before you call either

Amazon Polly

  1. Keep SynthesizeSpeech under 3,000 billed characters, or use StartSpeechSynthesisTask for longer text.
  2. Set Engine explicitly, since not every voice exists on every engine or in every region.
  3. Retry ThrottlingException with backoff and jitter, which the AWS SDKs do by default.
  4. Check the generative SSML tag list before porting neural SSML.
  5. Ask for OutputFormat json with speech marks when you need word timings.

ElevenLabs Text to Speech API + MCP

  1. Call Eleven v4 through POST /v1/text-to-dialogue and set model_id to eleven_v4, because that endpoint defaults to eleven_v3.
  2. Retrain an older Instant or Professional Voice Clone on v4 before using it there, since earlier clones aren't tuned for the new model.
  3. Spell out numbers yourself on eleven_flash_v2_5, which doesn't normalise them by default, and turning that on is Enterprise only.
  4. On 429 read code, back off on rate_limit_exceeded and wait for running requests on concurrent_limit_exceeded.
  5. Give the agent a key scoped to Text to Speech with a credit quota and, for a fixed server, an IP allowlist.

Questions

Which is better for AI agents, Amazon Polly or ElevenLabs Text to Speech API + MCP?

ElevenLabs Text to Speech API + MCP and Amazon Polly score within a point of each other on agent readiness, 77.8 (BB) and 77.2 (BB). Amazon Polly leads on security & auth and transparency & trust.

Do Amazon Polly and ElevenLabs Text to Speech API + MCP need an API key?

Amazon Polly needs an API key. ElevenLabs Text to Speech API + MCP takes an API key or an OAuth sign-in.

Can an agent call Amazon Polly and ElevenLabs Text to Speech API + MCP without installing anything?

Yes. Amazon Polly has a hosted endpoint at https://polly.us-east-1.amazonaws.com/v1 and ElevenLabs Text to Speech API + MCP at https://api.elevenlabs.io/v1.

Other comparisons with Amazon Polly or ElevenLabs Text to Speech API + MCP

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.