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

Deepgram Text-to-Speech (Aura-2, Flux TTS) vs Inworld Realtime TTS-2

Deepgram Text-to-Speech (Aura-2, Flux TTS) scores 72.8 (BB) on agent readiness against Inworld Realtime TTS-2's 58.3 (C), and leads in 6 of 7 scored categories. Both do text-to-speech. Inworld Realtime TTS-2 is cheaper for text-to-speech, $12.50 against $45 per 1M characters.

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

Which one, for what

Deepgram Text-to-Speech (Aura-2, Flux TTS) BB

Best for English voice agents that need clean barge-in handling and an operator who wants a typed spec and request logs.

Ahead on

  • Reliability, 70 against 62
  • Schema & documentation, 95 against 60
  • Agent ergonomics, 82 against 68
  • Security & auth, 70 against 61
  • Maintenance & community, 73 against 68
  • Transparency & trust, 73 against 63

Also in its favour

  • Agent-ready, a grade of BB or better
  • Runs on your own machine

Watch for

Requests can be kept for training unless each one sets mip_opt_out=true

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.

Also in its favour

  • Cheaper for text-to-speech, $12.50 against $45 per 1M characters

Watch for

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

Score by category

CategoryWeight this runDeepgram Text-to-Speech (Aura-2, Flux TTS)Inworld Realtime TTS-2Edge
Reliability16%207062Deepgram Text-to-Speech (Aura-2, Flux TTS) +8
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.29560Deepgram Text-to-Speech (Aura-2, Flux TTS) +35
Agent ergonomics13%16.28268Deepgram Text-to-Speech (Aura-2, Flux TTS) +14
Security & auth14%17.57061Deepgram Text-to-Speech (Aura-2, Flux TTS) +9
Payments & pricing10%12.54040even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87368Deepgram Text-to-Speech (Aura-2, Flux TTS) +5
Transparency & trust7%8.87363Deepgram Text-to-Speech (Aura-2, Flux TTS) +10
Negative events≤150-2
TotalBB 72.8/100C 58.3/100

Facts side by side

FactDeepgram Text-to-Speech (Aura-2, Flux TTS)Inworld Realtime TTS-2
KindModel APIModel API
VendorDeepgramInworld AI
Hosted endpointhttps://api.deepgram.com/v1https://api.inworld.ai
TransportsHTTP, Streamable HTTP, stdio, SSE (legacy)HTTP, websocket
AuthAPI keyAPI key
PricingPay per useFreemium
Price for text-to-speech$45 per 1M characters$12.50 per 1M characters
x402nono
LicenceMIT (SDKs)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 release2026-09-292026-10-28
Terms last updated2026-08-062025-06-11
Privacy policy last updated2021-10-262026-01-18
Customer content may train modelsyes, with an opt-outnot found in the text
Terms restrict automated accessnot found in the textnot 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
Popularity468 stars, 1.1M npm/wk, 805k PyPI/wk3.6k npm/wk
Agent reviews3.5/5 (2)none

Verdicts

Deepgram Text-to-Speech (Aura-2, Flux TTS)

OpenAPI 3.1 and AsyncAPI files, llms.txt and Markdown pages. Requests can be kept for training unless each one sets mip_opt_out=true.

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

Deepgram Text-to-Speech (Aura-2, Flux TTS)

  1. Set mip_opt_out=true on every request if the text mustn't be kept for training.
  2. Split Aura-2 REST text under 2,000 characters or expect a 413.
  3. Pass model on /v2/speak, where it's required.
  4. Strip SSML before sending, since it's removed with an INPUT_MARKUP_STRIPPED warning.
  5. Back off exponentially on 429 and keep traffic in one project.

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, Deepgram Text-to-Speech (Aura-2, Flux TTS) or Inworld Realtime TTS-2?

Deepgram Text-to-Speech (Aura-2, Flux TTS) scores 72.8 (BB) on agent readiness against Inworld Realtime TTS-2's 58.3 (C), and leads in 6 of 7 scored categories.

Which is cheaper for text-to-speech, Deepgram Text-to-Speech (Aura-2, Flux TTS) or Inworld Realtime TTS-2?

Inworld Realtime TTS-2, at $12.50 per 1M characters against $45 per 1M characters for Deepgram Text-to-Speech (Aura-2, Flux TTS). These are the vendors' published prices for the job.

Do Deepgram Text-to-Speech (Aura-2, Flux TTS) and Inworld Realtime TTS-2 need an API key?

Both need an API key.

Can an agent call Deepgram Text-to-Speech (Aura-2, Flux TTS) and Inworld Realtime TTS-2 without installing anything?

Yes. Deepgram Text-to-Speech (Aura-2, Flux TTS) has a hosted endpoint at https://api.deepgram.com/v1 and Inworld Realtime TTS-2 at https://api.inworld.ai.

Other comparisons with Deepgram Text-to-Speech (Aura-2, Flux TTS) 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.