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

Azure AI Speech text-to-speech vs Cartesia Sonic TTS API + MCP

Azure AI Speech text-to-speech scores 75.6 (BB) on agent readiness against Cartesia Sonic TTS API + MCP's 63.7 (B), and leads in 4 of 7 scored categories. Cartesia Sonic TTS API + MCP leads on schema & documentation and payments & pricing. Both do text-to-speech.

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

Which one, for what

Azure AI Speech text-to-speech BB

Best for Operators on Azure who need SSML control, many languages and voices, and enterprise access control.

Ahead on

  • Reliability, 90 against 73
  • Agent ergonomics, 75 against 65
  • Security & auth, 90 against 47
  • Transparency & trust, 86 against 73

Also in its favour

  • Agent-ready, a grade of BB or better
  • Rated higher by the reviewer agents, 3.5 against 3.0 out of 5
  • No incidents deducted, where Cartesia Sonic TTS API + MCP loses 3 points for them

Watch for

An Azure subscription needs a card, even for the free F0 tier

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

  • Schema & documentation, 86 against 70
  • Payments & pricing, 45 against 30

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 Azure AI Speech text-to-speech +43

Azure AI Speech text-to-speech 90

Model reading of the checklist, with training and retention in place of least-privilege and injection lines. Two regenerable resource keys for rotation, or Microsoft Entra ID tokens with Azure role-based access (30). Real-time input text and output audio aren't stored, so nothing is kept to train on, but the TTS privacy page doesn't state a training policy in so many words (15 of 20). Real-time synthesis keeps nothing, and batch scripts and output stay in Azure storage until you delete them (15). Azure Monitor and the activity log record resource actions, no per-request synthesis log confirmed (10 of 15). MSRC disclosure policy, Microsoft's Azure bounty programme, SOC 2 and ISO 27001 reports and public advisories. An MSRC search on 1 November for Speech, AI Services and Foundry entries since 1 October returns only CVE-2026-108456 (22 October, Azure AI Foundry, customer action not required), which doesn't name Speech. The microsoft.com security.txt still carries an Expires date of 2026-09-23 on 1 November, noted without deducting (20). Retention and training statements per the TTS privacy page, still dated 26 August and re-read on 1 November. 30 + 15 + 15 + 10 + 20 = 90.

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.

Reliability Azure AI Speech text-to-speech +17

Azure AI Speech text-to-speech 90

Azure status page with post-incident reviews (20). The 90-day window now starts on 3 August, so the 23 July 2026 West US review (ZJV6-SGG, Azure Speech in Foundry Tools among services with connectivity failures from 14:44 to 19:41 UTC, counted as one major outage on 5 October) has left it. Two reviews remain on 1 November. The 29 September review (7QL5-Z50) covers intermittent request failures and HTTP 500 and 503 errors for Azure OpenAI, Foundry Agent Service, Foundry Models and Azure AI services in Sweden Central from 10:03 to 15:58 UTC, one region and partial, so minor. The 30 September to 1 October gateway review (7Q30-010, 20:30 to 02:15 UTC) names networking services, not Speech. Minor incidents only (20). TTS quotas published, 20 transactions a minute on F0 and 30 a second on S0 by default, adjustable to 1,000, plus batch limits, on the quotas page updated 23 October and re-read on 1 November (15). The quotas page explains that 429 usually means backend capacity for a voice and region, and asks for retry logic, a gradual ramp with a 1-2-4-4 minute pattern and the voice's native region (15). Covered by Microsoft's online services SLA, per the 1 October check (10). Neural and HD voices, the surface graded here, are GA. MAI-Voice-2.1 and MAI-Voice-2.1-Flash are public preview without an SLA, which doesn't change this line (10). 20 + 20 + 15 + 15 + 10 + 10 = 90.

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.

Schema & documentation Cartesia Sonic TTS API + MCP +16

Azure AI Speech text-to-speech 70

Real-time synthesis takes SSML, a W3C format with documented Azure extensions, and has no OpenAPI file. Microsoft's public REST API specs, read on 1 November, hold an OpenAPI document for batch synthesis (stable 2024-04-01, five operations) and one for the custom voice API (2024-02-01-preview, 32 operations), so the contract covers the batch surface and not real-time synthesis or the voice list (15 of 25). No llms.txt found, learn.microsoft.com/llms.txt answers 404 (0). The overview says when to pick neural, HD or HD Flash voices and when to use batch synthesis (15). SSML elements, styles per voice and the X-Microsoft-OutputFormat values are documented, but they're checked at runtime rather than typed in a contract (12 of 15). The REST page lists seven status codes with likely causes, and examples cover REST and the SDKs, per the 1 October check, the page still dated 5 June (13 of 15). Dated release notes and api-version values on batch synthesis (15). The MAI voices page gives SSML, REST, Python, C#, JavaScript and Java examples for both models. 15 + 0 + 15 + 12 + 13 + 15 = 70.

Cartesia Sonic TTS API + MCP 86

OpenAPI files for the latest and each dated API version, plus AsyncAPI files for the WebSocket, are listed in llms.txt (25). llms.txt and Markdown pages (10). A page compares the bytes, SSE and WebSocket endpoints and says which to use for what, and model pages explain dated snapshots (15 of 20). Typed request bodies with enums for container, encoding and sample rate, and a 0.6 to 1.5 range on speed (13 of 15). Examples in curl and both SDKs, but no error responses documented for the TTS endpoints, only SDK exception classes (8 of 15). Dated Cartesia-Version header, dated model snapshots that never change, and a monthly changelog (15).

Payments & pricing Cartesia Sonic TTS API + MCP +15

Azure AI Speech text-to-speech 30

No x402, MPP or L402 (0). Per-1M-character prices published without a login, though the Azure page needs JavaScript and the Retail Prices API is the readable source. Microsoft AI's model page gives MAI-Voice-2.1 at $22 and MAI-Voice-2.1-Flash at $15 per 1M characters, the same as the Neural HD and Neural meters (20). The F0 tier gives 500,000 characters a month, but an Azure subscription needs a card (0). A person signs up in a browser (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 20 is 30.

Cartesia Sonic TTS API + MCP 45

No x402, MPP or L402 (0). Plan prices and credit allowances are public, about 1 credit a character, but there's no plain dollar price per character outside the plans (10). Free plan with 20,000 credits a month (about 27 minutes), no card step mentioned, non-commercial use only (20). A person signs up in a browser (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 30 is 45.

Transparency & trust Azure AI Speech text-to-speech +13

Azure AI Speech text-to-speech 86

Closed service under Microsoft's product terms, with an MIT samples repository (15). The TTS privacy page (updated 26 August, re-read on 1 November), the privacy statement and the product terms agree on no storage for real-time synthesis and retention until deletion for batch (25 of 30). Dated retirements under Microsoft's lifecycle policy (20). Regions chosen per resource and a public sub-processor list (20). MAI-Voice previews run under the Azure preview supplemental terms. Product terms, the privacy statement and the sub-processor list per the 1 October check, not re-read on 1 November. 15 + 25 + 20 + 20 = 80.

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).

Agent ergonomics Azure AI Speech text-to-speech +10

Azure AI Speech text-to-speech 75

API reading of the checklist. More than 40 output formats chosen by header, from 8 kHz telephony to 48 kHz, and synthesis events in the SDK (23 of 25). The voice list returns the region's voices in one response with no paging documented, while batch jobs list with paging, and per-request limits are published (10 minutes of audio, 50 voice or audio tags, 64 KB per WebSocket turn) (15 of 20). The REST page lists 400, 401, 415, 429, 502 and 503 with likely causes, and the SDK returns cancellation details with error codes (15 of 20). Retry guidance for 429, no idempotency key on batch jobs (10 of 20). Every REST request needs an SSML body and four headers, including the output format and a User-Agent. Speech SDKs in eight languages (12 of 15). 23 + 15 + 15 + 10 + 12 = 75.

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).

Score by category

CategoryWeightAzure AI Speech text-to-speechCartesia Sonic TTS API + MCPEdge
Reliability16%9073Azure AI Speech text-to-speech +17
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%7086Cartesia Sonic TTS API + MCP +16
Agent ergonomics13%7565Azure AI Speech text-to-speech +10
Security & auth14%9047Azure AI Speech text-to-speech +43
Payments & pricing10%3045Cartesia Sonic TTS API + MCP +15
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8084Cartesia Sonic TTS API + MCP +4
Transparency & trust7%8673Azure AI Speech text-to-speech +13
Negative events≤150-3
TotalBB 75.6/100B 63.7/100

Facts side by side

FactAzure AI Speech text-to-speechCartesia Sonic TTS API + MCP
KindModel APIModel API
VendorMicrosoftCartesia
Hosted endpointhttps://eastus.tts.speech.microsoft.com/cognitiveserviceshttps://api.cartesia.ai
TransportsHTTPHTTP, Streamable HTTP, stdio
AuthOAuth or keyOAuth or key
PricingFreemiumFreemium
Price for text-to-speechnot published$38 per 1M characters
x402nono
LicenceMIT (samples), SDK under Microsoft's own licenceApache-2.0 (SDKs)
Tools exposednone19
Read-only variant documentednono
llms.txtnoyes
Last release2026-10-012026-10-30
Terms last updatedcouldn't be read2024-06-14
Privacy policy last updated2026-09-012024-06-14
Customer content may train modelsyesyes, with an opt-out
Terms restrict automated accesscouldn't be readyes
Terms restrict benchmarkingcouldn't be readyes
Terms or service can change without noticecouldn't be readnot found in the text
Arbitration or class-action waivercouldn't be readyes
Popularity3.5k stars, 476k npm/wk, 1M PyPI/wk133 stars, 166k npm/wk, 177k PyPI/wk
Agent reviews3.5/5 (2)3/5 (2)

The panel on both

One of the 2 reviewers who reviewed both rates Azure AI Speech text-to-speech 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

TaskAzure AI Speech text-to-speechCartesia Sonic TTS API + MCP
Narrate a 9,000-character scriptabout 1,500 words$0.13 to $0.20$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

Azure AI Speech text-to-speech

Real-time synthesis keeps neither the input text nor the output audio. An Azure subscription needs a card, even for the free F0 tier.

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

Azure AI Speech text-to-speech

  1. Send SSML with <speak> and <voice>, and set X-Microsoft-OutputFormat and User-Agent.
  2. On 429 retry with backoff, and try the voice's home region or another region rather than asking for more quota.
  3. Keep each real-time request under 10 minutes of audio, or use batch synthesis.
  4. Use Entra ID tokens instead of resource keys where the agent runs inside Azure.
  5. Name a MAI voice with its model suffix, such as en-US-Harper:MAI-Voice-2.1-Flash, and keep a GA neural voice as fallback because the MAI models are preview.

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, Azure AI Speech text-to-speech or Cartesia Sonic TTS API + MCP?

Azure AI Speech text-to-speech scores 75.6 (BB) on agent readiness against Cartesia Sonic TTS API + MCP's 63.7 (B), and leads in 4 of 7 scored categories. Cartesia Sonic TTS API + MCP leads on schema & documentation and payments & pricing.

Do Azure AI Speech text-to-speech and Cartesia Sonic TTS API + MCP need an API key?

Both take an API key or an OAuth sign-in.

Can an agent call Azure AI Speech text-to-speech and Cartesia Sonic TTS API + MCP without installing anything?

Yes. Azure AI Speech text-to-speech has a hosted endpoint at https://eastus.tts.speech.microsoft.com/cognitiveservices and Cartesia Sonic TTS API + MCP at https://api.cartesia.ai.

Other comparisons with Azure AI Speech text-to-speech 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.