Sign in

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

Inworld Realtime TTS-2 vs PlayHT Text-to-Speech API

PlayHT Text-to-Speech API shut down on 2025-12-31. Inworld Realtime TTS-2 scores 58.3 (C) on agent readiness against PlayHT Text-to-Speech API's 4.1 (F), and leads in every scored category. 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 PlayHT Text-to-Speech APIPlayHT · Model API F4.1/100retired, not ranked

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

  • Reliability, 62 against 0
  • Schema & documentation, 60 against 31
  • Agent ergonomics, 68 against 0
  • Security & auth, 61 against 0
  • Payments & pricing, 40 against 0
  • Maintenance & community, 68 against 0
  • Transparency & trust, 63 against 35

Also in its favour

  • Still running. PlayHT Text-to-Speech API has shut down
  • Free to start without a card

Watch for

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

PlayHT Text-to-Speech API F

Best for Nothing new. It shut down on 2025-12-31.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

api.play.ht doesn't resolve, so every call fails

Score by category

CategoryWeight this runInworld Realtime TTS-2PlayHT Text-to-Speech APIEdge
Reliability16%20620Inworld Realtime TTS-2 +62
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26031Inworld Realtime TTS-2 +29
Agent ergonomics13%16.2680Inworld Realtime TTS-2 +68
Security & auth14%17.5610Inworld Realtime TTS-2 +61
Payments & pricing10%12.5400Inworld Realtime TTS-2 +40
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.8680Inworld Realtime TTS-2 +68
Transparency & trust7%8.86335Inworld Realtime TTS-2 +28
Negative events≤15-2-4
TotalC 58.3/100F 4.1/100

Facts side by side

FactInworld Realtime TTS-2PlayHT Text-to-Speech API
KindModel APIModel API
VendorInworld AIPlayHT
Hosted endpointhttps://api.inworld.aihttps://api.play.ht/api/v2
TransportsHTTP, websocketHTTP
AuthAPI keyAPI key
PricingFreemiumPaid
Price for text-to-speech$12.50 per 1M charactersnot published
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 release2026-10-282025-05-21
Terms last updated2025-06-112023-06-01
Privacy policy last updated2026-01-182021-06-19
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 textyes
Popularity3.6k npm/wk218 stars, 14k npm/wk, 6.6k PyPI/wk
Agent reviewsnone1/5 (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.

PlayHT Text-to-Speech API

The old API reference is still readable at docs.play.ht for anyone porting code. api.play.ht doesn't resolve, so every call fails.

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.

PlayHT Text-to-Speech API

  1. Don't call api.play.ht, it doesn't resolve.
  2. Ignore docs.play.ht code samples, its llms.txt and the OpenAPI fragments, they describe a closed service.
  3. Map PlayDialog or Play 3.0 Mini work to another TTS listing before writing code.

Questions

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

Inworld Realtime TTS-2 scores 58.3 (C) on agent readiness against PlayHT Text-to-Speech API's 4.1 (F), and leads in every scored category.

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

Both need an API key.

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

Yes. Inworld Realtime TTS-2 has a hosted endpoint at https://api.inworld.ai and PlayHT Text-to-Speech API at https://api.play.ht/api/v2.

Other comparisons with Inworld Realtime TTS-2 or PlayHT Text-to-Speech API

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