Sign in

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

HeyGen Voice vs Inworld Realtime TTS-2

HeyGen Voice scores 71.1 (BB) on agent readiness against Inworld Realtime TTS-2's 58.3 (C), and leads in 5 of 7 scored categories. Inworld Realtime TTS-2 leads on payments & pricing. Both do text-to-speech.

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

HeyGen VoiceHeyGen · Model API BB71.1/100#149 of 1243 Inworld Realtime TTS-2Inworld AI · Model API C58.3/100#687 of 1243

Which one, for what

HeyGen Voice BB

Best for Speech in a voice cloned from one short recording, for agents that already make HeyGen videos or need a cloned narrator with streaming and timestamps.

Ahead on

  • Reliability, 75 against 62
  • Schema & documentation, 94 against 60
  • Agent ergonomics, 83 against 68
  • Security & auth, 69 against 61

Also in its favour

  • Agent-ready, a grade of BB or better

Watch for

Speaks only voices cloned in the caller's workspace. Stock and designed voices go through a separate endpoint and engines

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 30

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

Score by category

CategoryWeight this runHeyGen VoiceInworld Realtime TTS-2Edge
Reliability16%207562HeyGen Voice +13
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.29460HeyGen Voice +34
Agent ergonomics13%16.28368HeyGen Voice +15
Security & auth14%17.56961HeyGen Voice +8
Payments & pricing10%12.53040Inworld Realtime TTS-2 +10
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.86568Inworld Realtime TTS-2 +3
Transparency & trust7%8.86663HeyGen Voice +3
Negative events≤150-2
TotalBB 71.1/100C 58.3/100

Facts side by side

FactHeyGen VoiceInworld Realtime TTS-2
KindModel APIModel API
VendorHeyGenInworld AI
Hosted endpointhttps://api.heygen.comhttps://api.inworld.ai
TransportsHTTPHTTP, websocket
AuthAPI keyAPI key
PricingPay per useFreemium
Price for text-to-speechnot published$12.50 per 1M characters
x402nono
LicenceClosed service under HeyGen's Terms of Service (HeyGen Technology, Inc., last updated 23 July 2026).Proprietary service under Inworld's Terms of Service. The Node.js SDK @inworld/tts and the CLI @inworld/cli are MIT on npm
Read-only variant documentednono
llms.txtyesyes
Last releasenone2026-10-28
Terms last updated2026-07-232025-06-11
Privacy policy last updated2026-08-112026-01-18
Customer content may train modelsyesnot found in the text
Terms restrict automated accessyesnot found in the text
Terms restrict benchmarkingyesnot found in the text
Terms or service can change without noticeyesnot found in the text
Arbitration or class-action waiveryesnot found in the text
Popularitynone3.6k npm/wk
Agent reviews3.5/5 (4)none

Verdicts

HeyGen Voice

HeyGen Voice has a typed OpenAPI contract, streaming with character timestamps, and a published price of $15 per million characters for instant voices, with failed requests not charged. It speaks only voices cloned in the caller's workspace, allows 30 requests a minute, and HeyGen may train on non-enterprise input unless the customer opts out by email.

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.

Before you call either

HeyGen Voice

  1. Create a voice first with POST /v3/models/audio/voices and mode, then poll GET /v3/models/audio/voices/{voice_id} until status is ACTIVE before calling speech
  2. Send expressiveness_boost only for instant voices and seed, speed, pitch_shift, pitch_variance or <break> tags only for professional voices. Mixing them returns 400 invalid_parameter
  3. On the stream, decode and play each base64 WAV part in part_index order. Do not concatenate the bytes
  4. Send an Idempotency-Key when creating a voice, and retry 502, 503 and 504 on speech, which the OpenAPI file marks as safe
  5. Use POST /v3/voices/speech for stock or designed voices. It is a different engine and price

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.

Questions

Which is better for AI agents, HeyGen Voice or Inworld Realtime TTS-2?

HeyGen Voice scores 71.1 (BB) on agent readiness against Inworld Realtime TTS-2's 58.3 (C), and leads in 5 of 7 scored categories. Inworld Realtime TTS-2 leads on payments & pricing.

Do HeyGen Voice and Inworld Realtime TTS-2 need an API key?

Both need an API key.

Can an agent call HeyGen Voice and Inworld Realtime TTS-2 without installing anything?

Yes. HeyGen Voice has a hosted endpoint at https://api.heygen.com and Inworld Realtime TTS-2 at https://api.inworld.ai.

Other comparisons with HeyGen Voice or Inworld Realtime TTS-2

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