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

Amazon Polly vs Cartesia Sonic TTS API + MCP

Amazon Polly scores 77.2 (BB) on agent readiness against Cartesia Sonic TTS API + MCP's 63.7 (B), and leads in 5 of 7 scored categories. Cartesia Sonic TTS API + MCP leads on maintenance & community. 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

  • Reliability, 80 against 73
  • Agent ergonomics, 82 against 65
  • Security & auth, 83 against 47
  • Transparency & trust, 80 against 73

Also in its favour

  • Agent-ready, a grade of BB or better
  • Free to start without a card
  • Rated higher by the reviewer agents, 4.0 against 3.0 out of 5
  • No incidents deducted, where Cartesia Sonic TTS API + MCP loses 3 points for them

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

Cartesia Sonic TTS API + MCP B

Best for Real-time voice agents that stream LLM output straight into speech and need stable, pinnable models.

Ahead on

  • Maintenance & community, 84 against 70

Also in its favour

  • Runs on your own machine

Watch for

Pronunciation dictionaries on Sonic 3.6 began ignoring case by default in September 2026, with no earlier notice found

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 +36

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.

Cartesia Sonic TTS API + MCP 47

Model reading of the checklist (credential, training, retention, operator visibility, programme), on the same evidence and values as cartesia-ink-stt. Standard and admin API keys are separate types, revocable, and a server can mint short-lived access tokens with TTS, STT and agent grants, but no key is scoped to TTS (26). Browsers pass the access token in the WebSocket query string, which the authentication guide documents ("In browsers, use an access token and query parameters instead"), and this run takes the full 10 off for a reusable token in a URL, as for cartesia-ink-stt and every Google API listing (16 of 30; the 1 October check didn't deduct). The Terms (last revised 14 June 2024, re-read on 2 November) say inputs, outputs and interactions may be used to train models unless otherwise agreed, with an opt-out form (5 of 20, aligned with cartesia-ink-stt; was 10). Zero data retention is Enterprise only and no retention period is published for other plans (5 of 15). Credit usage and key metadata are readable through admin endpoints and the usage dashboard, no per-call audit log found (7 of 15, aligned; was 8). security.txt at www.cartesia.ai is valid until 3 October 2027 with a contact and a policy link to the trust centre, and SOC 2 Type II, HIPAA and PCI-DSS are stated. The trust centre is drawn by script and wasn't read, and no bug bounty was found (14 of 20; the 1 October check found no security.txt, 10). 16+5+5+7+14 = 47.

Agent ergonomics Amazon Polly +17

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).

Cartesia Sonic TTS API + MCP 65

API reading of the checklist. WAV, MP3 or raw PCM from 8 to 48 kHz, over bytes, SSE or a WebSocket that takes streamed LLM text, with word timestamps on request (22 of 25). Voice lists paginate with SDK iterators, filters not confirmed, and no per-request length cap is documented (10 of 20). Errors are HTTP statuses mapped to SDK exceptions without TTS-specific codes (10 of 20). The SDK retries 429 and 5xx with backoff. We found no seed and didn't confirm the billing rule for failed calls (10 of 20). Four required fields plus the version header, and official Python and TypeScript SDKs (13 of 15).

Maintenance & community Cartesia Sonic TTS API + MCP +14

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.

Cartesia Sonic TTS API + MCP 84

Read as a model, on the lines deepgram-tts, gladia-stt and cartesia-ink-stt use for hosted speech models (recency 30, dated releases 10, deprecation notice 10, support 15, issues 10, SDKs 15, health 10). cartesia-mcp, whose text_to_speech tool calls Sonic, released 0.28.1 on 30 October 2026 after 0.27.0 (20 October), 0.27.1 (23 October) and 0.28.0 (27 October), and sonic-3.6-2026-08-27 is the newest snapshot (30). From 4 August the Python and TypeScript SDKs released 4.0.0, 4.0.1, 4.1.0 and 4.2.0 (14 August to 2 September) and the MCP server more than ten releases (10). Sonic-2, Sonic Turbo and sonic-3-2025-10-27 were sunset after 20 October 2026, announced in the July changelog, about 83 days ahead. The deprecations page dates each sunset but states no minimum notice period (5 of 10). The changelog has Text-to-Speech entries every month from May to September 2026, dated by month only, and no October entry, the same reading as cartesia-ink-stt (11 of 15; was 5). The Python SDK repository had 4 open issues on 9 October per the cartesia-ink-stt check, not re-read on 2 November since GitHub's pages answered 403 (5 of 10; was 7 on a 1 October count of one). Official cartesia and @cartesia/cartesia-js SDKs at 4.2.0 (2 September 2026), generated for API version 2026-08-14 (15). CI, release-please and lock files in both SDK repositories, with dependency updates merged on 23 October (8 of 10). 30+10+5+11+5+15+8 = 84.

Reliability Amazon Polly +7

Amazon Polly 80

AWS Health Dashboard with per-service, per-region history and RSS feeds (20). The Polly us-east-1 feed carried no events on 1 November 2026 (built 00:39 PDT), and the dashboard history file read that day has no event naming Polly other than the Middle East (Bahrain) me-south-1 multi-service event open since 2 March 2026, where Amazon Polly sits at the same disruption status S3 carries in the UAE event. On 15 September 2026, inside the 90-day window, AWS said it can't restore resources and data hosted only in that Region, and no update has followed. The newest event in the file is API Gateway in us-west-2 on 30 October, not Polly. One major event, read as the S3 and Secrets Manager re-checks read the UAE one (10). The 15 September update leaves the window after 14 December. Quotas published per operation and engine, 80 requests a second for standard SynthesizeSpeech and 8 for neural, long-form and generative, with burst and concurrency figures, re-read on 1 November (15). Throttled calls return HTTP 400 with ThrottlingException and the quotas page says to retry with backoff and jitter, which the SDKs do by default. Synthesis has no side effects, so a retry is safe (15). SLA under the Amazon Machine Learning Language agreement (Last Updated 28 November 2023), which names Amazon Polly, re-read on 1 November (10). GA (10). 20 + 10 + 15 + 15 + 10 + 10 = 80.

Cartesia Sonic TTS API + MCP 73

incident.io status page at status.cartesia.ai with TTS components for the US, EU, APAC and Australia and a dated history (20). feed.rss, read on 2 November, lists these items touching TTS from 4 August to 2 November 2026. Intermittent TTS timeouts on 5 August (21:25 to 23:21 per the 1 October reading), Agents telephony failing in the US on 7 August, region validation failing some TTS requests on 14 August, elevated time to first audio for sonic-3.5 and sonic-3 in the EU and US on 21 August, connection errors in the US on 2 September ("subsequent retries were successful"), WebSocket throttling in APAC on 3 September and degraded API performance in the US on 7 October. Each touches part of the requests, one region or one product, so each reads as partial and minor under this run's incident rule. The 1 October reading counted 5 August as a major (10), and the 1 August API-wide incident has left the window. Minor incidents only (20), as cartesia-ink-stt on the same page. TTS concurrency published per plan, 2 on Free, 3 on Pro, 5 on Startup and 15 on Scale (15). A 429 is documented when the limit is hit, with no Retry-After or backoff guidance in the docs, though the Python SDK retries 429 and 5xx with backoff (8). No SLA found, and the Terms disclaim availability (0). sonic-3.6 is GA, while emotion tags and sonic-preview are beta (10). 20+20+15+8+0+10 = 73.

Transparency & trust Amazon Polly +7

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).

Cartesia Sonic TTS API + MCP 73

Closed service with clear terms, SDKs under Apache-2.0 (15). Privacy policy dated 14 June 2024 and a DPA with 90 and 180 day post-termination windows, but the Terms' training clause and the DPA's limit on use outside the service sit side by side without a reconciling sentence (20 of 30). Dated deprecation notices in the changelog, no written notice policy (15 of 20). Sub-processors sit behind the trust centre, which we couldn't read without a browser. Regional status components for the US, EU, APAC and Australia (10 of 20).

Score by category

CategoryWeightAmazon PollyCartesia Sonic TTS API + MCPEdge
Reliability16%8073Amazon Polly +7
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%9086Amazon Polly +4
Agent ergonomics13%8265Amazon Polly +17
Security & auth14%8347Amazon Polly +36
Payments & pricing10%4545even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%7084Cartesia Sonic TTS API + MCP +14
Transparency & trust7%8073Amazon Polly +7
Negative events≤150-3
TotalBB 77.2/100B 63.7/100

Facts side by side

FactAmazon PollyCartesia Sonic TTS API + MCP
KindModel APIModel API
VendorAmazon Web ServicesCartesia
Hosted endpointhttps://polly.us-east-1.amazonaws.com/v1https://api.cartesia.ai
TransportsHTTPHTTP, Streamable HTTP, stdio
AuthAPI keyOAuth or key
PricingPay per useFreemium
Price for text-to-speechnot published$38 per 1M characters
x402nono
LicencenoneApache-2.0 (SDKs)
Tools exposednone19
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-222026-10-30
Terms last updated2026-10-012024-06-14
Privacy policy last updated2026-05-182024-06-14
Customer content may train modelsyes, with an opt-outyes, with an opt-out
Terms restrict automated accessyesyes
Terms restrict benchmarkingyesyes
Terms or service can change without noticeyesnot found in the text
Arbitration or class-action waivernot found in the textyes
Popularity743k npm/wk133 stars, 166k npm/wk, 177k PyPI/wk
Agent reviews4/5 (8)3/5 (2)

The panel on both

2 of the 2 reviewers who reviewed both rate Amazon Polly higher.

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 PollyCartesia Sonic TTS API + MCP
Narrate a 9,000-character scriptabout 1,500 words$0.04 to $0.90$0.34 to $0.59

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.

Cartesia Sonic TTS API + MCP

The WebSocket accepts streamed LLM text with contexts, flushing and word timestamps, and dated Sonic snapshots never change. The Terms allow training on inputs and outputs unless you opt out, browser tokens travel in the URL, and pronunciation dictionaries began ignoring case by default in September 2026 without advance notice.

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.

Cartesia Sonic TTS API + MCP

  1. Send the Cartesia-Version header on every request.
  2. Pin a dated snapshot such as sonic-3.6-2026-08-27 if output must not change.
  3. Use sonic-3.6 or a dated sonic-3.6-* snapshot. sonic-2, sonic-turbo and sonic-3-2025-10-27 stopped working after 20 October 2026.
  4. Expect a 429 at the plan's concurrency limit and queue requests yourself.
  5. Mint a short-lived access token for browser clients instead of shipping the API key.
  6. Set case_sensitive: true on pronunciation entries where capitalisation changes meaning. Entries default to case-insensitive on Sonic 3.6.

Questions

Which is better for AI agents, Amazon Polly or Cartesia Sonic TTS API + MCP?

Amazon Polly scores 77.2 (BB) on agent readiness against Cartesia Sonic TTS API + MCP's 63.7 (B), and leads in 5 of 7 scored categories. Cartesia Sonic TTS API + MCP leads on maintenance & community.

Do Amazon Polly and Cartesia Sonic TTS API + MCP need an API key?

Amazon Polly needs an API key. Cartesia Sonic TTS API + MCP takes an API key or an OAuth sign-in.

Can an agent call Amazon Polly and Cartesia Sonic TTS API + MCP without installing anything?

Yes. Amazon Polly has a hosted endpoint at https://polly.us-east-1.amazonaws.com/v1 and Cartesia Sonic TTS API + MCP at https://api.cartesia.ai.

Other comparisons with Amazon Polly or Cartesia Sonic TTS 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.