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

Azure AI Speech text-to-speech vs Soniox Text-to-Speech

Azure AI Speech text-to-speech scores 75.6 (BB) on agent readiness against Soniox Text-to-Speech's 71.8 (BB), and leads in 4 of 7 scored categories. Soniox Text-to-Speech leads on schema & documentation. 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

  • Maintenance & community, 80 against 63
  • Transparency & trust, 86 against 73

Also in its favour

  • Rated higher by the reviewer agents, 3.5 against 3.0 out of 5
  • No incidents deducted, where Soniox Text-to-Speech loses 3 points for them

Watch for

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

Soniox Text-to-Speech BB

Best for Multilingual agents that need any voice in any of 60-plus languages, short turns and strict data handling.

Ahead on

  • Schema & documentation, 85 against 70

Watch for

Audio stops at 2 minutes per request or stream and the cap can't be raised

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.

Maintenance & community Azure AI Speech text-to-speech +17

Azure AI Speech text-to-speech 80

Read as a model. The newest dated text-to-speech change is MAI-Voice-2.1 and MAI-Voice-2.1-Flash entering public preview on 1 October 2026 (MAI voices page, updated 1 October), 31 days before 1 November (20). Speech SDK 1.52 (September 2026, on NuGet on 28 September) fixes an embedded TTS timeout and two TTS crashes with compressed audio, and 1.51.2 (August 2026, on NuGet on 20 August) fixes a crash on speech synthesis and a Java synthesis handle error, per Microsoft's release notes, so both are dated releases that change the synthesis client, as azure-translator's 2.0.3 client fix was counted. Speech SDK 1.53.0 (JavaScript tag of 21 October, on NuGet on 22 October) adds inline commit support for pushed audio input, the JavaScript diff touches only recognition code and the release notes have no 1.53 entry yet, so it counts half and doesn't set recency. Three dated text-to-speech changes in the 90 days from 3 August, MAI-Voice-2.1 on 1 October, SDK 1.52 and SDK 1.51.2 (20). Retirements follow Microsoft's published lifecycle policy with dated notices. The MAI model has turned over three times since March 2026 (MAI-Voice-1, MAI-Voice-2-Flash, MAI-Voice-2.1), and the MAI page dropped MAI-Voice-2-Flash without a dated notice, while the language list still carries it (10). Public release notes and Microsoft Q&A, SDK issue tracker not checked (10 of 25). Speech SDK current in eight languages (15). The SDK is a closed binary, so we can't see its CI (5 of 10). 20 + 20 + 10 + 10 + 15 + 5 = 80.

Soniox Text-to-Speech 63

Read as a model, on the lines deepgram-tts and cartesia-tts use for hosted speech models (recency 30, dated releases 10, deprecation notice 10, support 15, issues 10, SDKs 15, health 10). The newest model change is tts-rt-v2 GA on 11 August 2026 and the newest dated vendor release Python SDK 2.10.0 on 2 October, 31 days before 2 November (20). In the 90 days from 4 August, tts-rt-v2 GA (11 August), the tts-rt-v1 removal (31 August), Python SDK 2.9.0 (11 August) and 2.10.0 (2 October), and the JavaScript SDK tag v2026.08.11 (10 August, counted half) (10; was 0). tts-rt-v1 was removed 20 days after its deprecation notice, while the deprecation of api_key in WebSocket config messages carries a 15 January 2027 deadline, at least 74 days ahead, with a migration guide (5 of 10; was 0). The models page and a support channel, untested (5 of 15). SDK issues couldn't be read because GitHub's pages answered 403 (3 of 10). SDKs for Python, Node, the web and React (15). The Python SDK has a test suite and lock file, but its CI file sits in .github/ rather than .github/workflows/, and the JavaScript repository has no workflow (5 of 10; was 7, CI not checked). 20 + 10 + 5 + 5 + 3 + 15 + 5 = 63.

Schema & documentation Soniox Text-to-Speech +15

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.

Soniox Text-to-Speech 85

Soniox now publishes an OpenAPI 3.1.0 file at docs.soniox.com/openapi.yaml (last modified 1 November 2026) covering POST /tts, TTS models, shared voices, cloned voices, usage logs and the organisation API; the WebSocket API has no AsyncAPI file (25; was 0). llms.txt and .mdx pages, now on docs.soniox.com (10). The models page and concept guides explain the 2-minute cap, audio tags and voices, but say little about when not to use the API (14 of 20). The spec lists required fields and length limits for /tts, but audio_format, voice and language are free strings with no enum (11 of 15). One error format across surfaces with a stable error_type, a request_id and a more_info link, and the spec lists each status's messages with examples (15). Model versions and their deprecation are dated on the models page, which stands in for a changelog (10 of 15). 25 + 10 + 14 + 11 + 15 + 10 = 85.

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.

Soniox Text-to-Speech 73

Closed service under terms updated 2026-06-29, Python SDK under Apache-2.0 (15). The security page, the terms and the TTS docs agree on no storage and no training, with async data deleted after 30 days (25 of 30). Model removals are dated on the models page with 20 days' notice for v1, and the WebSocket authentication change is dated to 15 January 2027 with a migration guide, but there is no written policy (12 of 20; was 10). Regional hosts in the US, EU, Japan and India and a data residency page, no sub-processor list found (12 of 20). 15 + 25 + 12 + 12 = 64.

Score by category

CategoryWeightAzure AI Speech text-to-speechSoniox Text-to-SpeechEdge
Reliability16%9087Azure AI Speech text-to-speech +3
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%7085Soniox Text-to-Speech +15
Agent ergonomics13%7578Soniox Text-to-Speech +3
Security & auth14%9087Azure AI Speech text-to-speech +3
Payments & pricing10%3030even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8063Azure AI Speech text-to-speech +17
Transparency & trust7%8673Azure AI Speech text-to-speech +13
Negative events≤150-3
TotalBB 75.6/100BB 71.8/100

Facts side by side

FactAzure AI Speech text-to-speechSoniox Text-to-Speech
KindModel APIModel API
VendorMicrosoftSoniox
Hosted endpointhttps://eastus.tts.speech.microsoft.com/cognitiveserviceshttps://tts-rt.soniox.com
TransportsHTTPHTTP
AuthOAuth or keyAPI key
PricingFreemiumPay per use
Price for text-to-speechnot published$0.0117 per minute of audio
x402nono
LicenceMIT (samples), SDK under Microsoft's own licenceApache-2.0 (Python SDK)
Read-only variant documentednono
llms.txtnoyes
Last release2026-10-012026-10-02
Terms last updatedcouldn't be read2026-06-29
Privacy policy last updated2026-09-012026-06-29
Customer content may train modelsyesnot found in the text
Terms restrict automated accesscouldn't be readnot found in the text
Terms restrict benchmarkingcouldn't be readyes
Terms or service can change without noticecouldn't be readyes
Arbitration or class-action waivercouldn't be readnot found in the text
Popularity3.5k stars, 476k npm/wk, 1M PyPI/wk12 stars, 22k npm/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.

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.

Soniox Text-to-Speech

Content is not stored by default or used for training, keys carry per-resource permissions, an OpenAPI file covers the REST endpoint, and no TTS incident was posted in the 90 days to 2 November. Audio stops at two minutes per request, and Python SDK 2.10.0 removed public interfaces in a minor release without 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.

Soniox Text-to-Speech

  1. Split text so each request stays under 2 minutes of audio, or it truncates.
  2. Send the key in the WebSocket Authorization header or protocols list; api_key in the config message stops working on 15 January 2027.
  3. Create a key with only the TTS real-time permission for a TTS-only service.
  4. Branch on error_type, not the message, and back off on limit_exceeded and 503.
  5. Pick the regional host (EU, Japan, India) that matches your data residency.

Questions

Which is better for AI agents, Azure AI Speech text-to-speech or Soniox Text-to-Speech?

Azure AI Speech text-to-speech scores 75.6 (BB) on agent readiness against Soniox Text-to-Speech's 71.8 (BB), and leads in 4 of 7 scored categories. Soniox Text-to-Speech leads on schema & documentation.

Do Azure AI Speech text-to-speech and Soniox Text-to-Speech need an API key?

Azure AI Speech text-to-speech takes an API key or an OAuth sign-in. Soniox Text-to-Speech needs an API key.

Can an agent call Azure AI Speech text-to-speech and Soniox Text-to-Speech without installing anything?

Yes. Azure AI Speech text-to-speech has a hosted endpoint at https://eastus.tts.speech.microsoft.com/cognitiveservices and Soniox Text-to-Speech at https://tts-rt.soniox.com.

Other comparisons with Azure AI Speech text-to-speech or Soniox Text-to-Speech

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.