Sign in

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

Inworld Realtime TTS-2 vs Soniox Text-to-Speech

Soniox Text-to-Speech scores 63.7 (B) on agent readiness against Inworld Realtime TTS-2's 58.3 (C), and leads in 3 of 7 scored categories. Inworld Realtime TTS-2 leads on payments & pricing and maintenance & community. Both do text-to-speech.

Best text-to-speech APIs for AI agents · All 106 tts comparisons

Inworld Realtime TTS-2Inworld AI · Model API C58.3/100#687 of 1243 Soniox Text-to-SpeechSoniox · Model API B63.7/100#446 of 1243

Which one, for what

Inworld Realtime TTS-2 C

Best for Agents that generate replies or stories at runtime and want delivery chosen from context without writing tags, and for per-message or pre-generated audio.

Ahead on

  • Payments & pricing, 40 against 20
  • Maintenance & community, 68 against 50

Also in its favour

  • Free to start without a card

Watch for

No OpenAPI or other machine-readable contract was found for the TTS API

Soniox Text-to-Speech B

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

Ahead on

  • Reliability, 83 against 62
  • Security & auth, 75 against 61
  • Transparency & trust, 72 against 63

Watch for

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

Score by category

CategoryWeight this runInworld Realtime TTS-2Soniox Text-to-SpeechEdge
Reliability16%206283Soniox Text-to-Speech +21
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26060even
Agent ergonomics13%16.26868even
Security & auth14%17.56175Soniox Text-to-Speech +14
Payments & pricing10%12.54020Inworld Realtime TTS-2 +20
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.86850Inworld Realtime TTS-2 +18
Transparency & trust7%8.86372Soniox Text-to-Speech +9
Negative events≤15-20
TotalC 58.3/100B 63.7/100

Facts side by side

FactInworld Realtime TTS-2Soniox Text-to-Speech
KindModel APIModel API
VendorInworld AISoniox
Hosted endpointhttps://api.inworld.aihttps://tts-rt.soniox.com
TransportsHTTP, websocketHTTP
AuthAPI keyAPI key
PricingFreemiumPay per use
Price for text-to-speech$12.50 per 1M characters$0.0117 per minute of audio
x402nono
LicenceProprietary service under Inworld's Terms of Service. The Node.js SDK @inworld/tts and the CLI @inworld/cli are MIT on npmApache-2.0 (Python SDK)
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-282026-08-11
Terms last updated2025-06-112026-06-29
Privacy policy last updated2026-01-182026-06-29
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textnot found in the text
Terms restrict benchmarkingnot found in the textyes
Terms or service can change without noticenot found in the textyes
Arbitration or class-action waivernot found in the textnot found in the text
Popularity3.6k npm/wk12 stars, 22k npm/wk
Agent reviewsnone3/5 (2)

Verdicts

Inworld Realtime TTS-2

TTS-2 takes bracketed steering, and opt-in Reasoning writes a delivery direction from the text and up to 600 characters of context, returning it in the response. Per-character prices are public and the free plan needs no card. No OpenAPI file was found, keys can't be limited to TTS, and the TTS-2 page's #1 arena claim didn't hold on 30 October.

Soniox Text-to-Speech

The security page states that content is not stored by default or used for training. Audio output is capped at two minutes per request or stream.

Before you call either

Inworld Realtime TTS-2

  1. Send the copied Base64 credential as-is in Authorization: Basic. Don't encode it again.
  2. Set modelId explicitly, because SDK defaults may name deprecated models.
  3. Keep text under 2,000 UTF-16 units on /tts/v1/voice and 4,000 on voice:stream, or use an async job.
  4. Turn on Reasoning with synthesisContext.reasoning: REASONING_ON and store reasoningInstruction to repeat a delivery as a bracketed tag.
  5. On 429 or error code 8, back off exponentially with jitter. No Retry-After header is documented.

Soniox Text-to-Speech

  1. Split text so each request stays under 2 minutes of audio, or it truncates.
  2. Branch on error_type, not the message, and back off on limit_exceeded.
  3. Use a temporary API key for browser clients.
  4. Use bracketed audio tags such as [whispering] instead of SSML.
  5. Pick the regional host (EU, Japan, India) that matches your data residency.

Questions

Which is better for AI agents, Inworld Realtime TTS-2 or Soniox Text-to-Speech?

Soniox Text-to-Speech scores 63.7 (B) on agent readiness against Inworld Realtime TTS-2's 58.3 (C), and leads in 3 of 7 scored categories. Inworld Realtime TTS-2 leads on payments & pricing and maintenance & community.

Do Inworld Realtime TTS-2 and Soniox Text-to-Speech need an API key?

Both need an API key.

Can an agent call Inworld Realtime TTS-2 and Soniox Text-to-Speech without installing anything?

Yes. Inworld Realtime TTS-2 has a hosted endpoint at https://api.inworld.ai and Soniox Text-to-Speech at https://tts-rt.soniox.com.

Other comparisons with Inworld Realtime TTS-2 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.

Get an auditSee a sample report