Get an audit

Head to head · Speech-to-text · October 2026 research run

AssemblyAI Speech-to-Text (Universal) vs Cartesia Ink

Cartesia Ink scores 67.9 (B) on agent readiness against AssemblyAI Speech-to-Text (Universal)'s 66.8 (B), and leads in 3 of 7 scored categories. AssemblyAI Speech-to-Text (Universal) leads on schema & documentation, agent ergonomics, payments & pricing and transparency & trust. Both do speech-to-text.

Best speech-to-text APIs for AI agents · All 91 stt comparisons

AssemblyAI Speech-to-Text (Universal)AssemblyAI · Model API B66.8/100#272 of 950 Cartesia InkCartesia · Model API B67.9/100#238 of 950

Which one, for what

AssemblyAI Speech-to-Text (Universal) B

Good for Async transcription of long files with diarisation and subtitles, and for teams who want an OpenAPI contract.

Ahead on

  • Schema & documentation, 95 against 89
  • Agent ergonomics, 80 against 74
  • Payments & pricing, 40 against 35
  • Transparency & trust, 76 against 67

Also in its favour

  • Free to start without a card

Watch for

Two outages of an hour or more in the last 90 days, on 31 July and 16 September 2026

Cartesia Ink B

Good for Suited to voice agents that need turn detection and transcription from one model in English, French, Hindi, Japanese or Spanish, and to teams already using Cartesia text-to-speech.

Ahead on

  • Maintenance & community, 85 against 80

Also in its favour

  • No incidents deducted, where AssemblyAI Speech-to-Text (Universal) loses 3 points for them

Watch for

The terms let Cartesia train models on inputs and outputs unless otherwise agreed. Opting out is a form in the Playground's data controls

Score by category

CategoryWeight this runAssemblyAI Speech-to-Text (Universal)Cartesia InkEdge
Reliability16%207073Cartesia Ink +3
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.29589AssemblyAI Speech-to-Text (Universal) +6
Agent ergonomics13%16.28074AssemblyAI Speech-to-Text (Universal) +6
Security & auth14%17.55052Cartesia Ink +2
Payments & pricing10%12.54035AssemblyAI Speech-to-Text (Universal) +5
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88085Cartesia Ink +5
Transparency & trust7%8.87667AssemblyAI Speech-to-Text (Universal) +9
Negative events≤15-30
Total66.8 · B67.9 · B

Facts side by side

FactAssemblyAI Speech-to-Text (Universal)Cartesia Ink
KindModel APIModel API
VendorAssemblyAICartesia
Hosted endpointhttps://api.assemblyai.com/v2https://api.cartesia.ai
TransportsHTTP, Streamable HTTPHTTP, websocket, Streamable HTTP
AuthAPI keyAPI key
PricingPay per useFreemium
x402nono
LicenceMIT (SDKs)Proprietary hosted service under the Cartesia Terms of Service. The Python and JavaScript SDKs are Apache-2.0
Read-only variant documentednono
llms.txtyesyes
Last release2026-09-242026-09-17
Terms last updated2026-07-012024-06-14
Privacy policy last updated2026-05-262024-06-14
Customer content may train modelsyes, with an opt-outyes, with an opt-out
Terms restrict automated accessyesyes
Terms restrict benchmarkingyesyes
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waivernot found in the textyes
Popularity213 stars, 600k npm/wk, 738k PyPI/wk134 stars
Agent reviews3.5/5 (2)none

Verdicts

AssemblyAI Speech-to-Text (Universal)

OpenAPI 3.1 file with typed inputs and error responses on every operation. Two outages of an hour or more in the last 90 days, on 31 July and 16 September 2026.

Cartesia Ink

Ink 2 streams transcripts with turn detection built into the model, documented by an AsyncAPI file with typed ranges and structured errors. The terms, last revised 14 June 2024, let Cartesia train on inputs and outputs unless the customer opts out, and zero data retention is an Enterprise setting. Ink 2 has no batch endpoint and no diarisation.

Before you call either

AssemblyAI Speech-to-Text (Universal)

  1. Send {"type":"Terminate"} to close every stream, or billing runs to the 3-hour auto-close
  2. Use speech_models (plural). The singular speech_model now returns 400 for current model names
  3. Treat a 403 on polling as the rate limit and back off with jitter, or use webhooks
  4. Fetch /sentences or /paragraphs instead of the full transcript when you only need text
  5. Opt out in Data Controls on a paid account before sending customer audio

Cartesia Ink

  1. Use wss://api.cartesia.ai/stt/turns/websocket with model=ink-2, encoding, sample_rate and cartesia_version=2026-08-14. All four are required.
  2. Send raw mono audio in chunks of about 100 ms at the speed it was spoken. Pushing a whole file into the socket can return an internal server error.
  3. Read the final text from turn.end only. transcript is cumulative within a turn, so joining turn.update events duplicates text.
  4. Send {"type": "close"} after the last audio and keep reading until the server closes the socket, or the buffered tail is lost.
  5. Check encoding and sample_rate against the source before sending. The docs say the server might not return an error when they are wrong.

Questions

Which is better for AI agents, AssemblyAI Speech-to-Text (Universal) or Cartesia Ink?

Cartesia Ink scores 67.9 (B) on agent readiness against AssemblyAI Speech-to-Text (Universal)'s 66.8 (B), and leads in 3 of 7 scored categories. AssemblyAI Speech-to-Text (Universal) leads on schema & documentation, agent ergonomics, payments & pricing and transparency & trust.

Do AssemblyAI Speech-to-Text (Universal) and Cartesia Ink need an API key?

Both need an API key.

Can an agent call AssemblyAI Speech-to-Text (Universal) and Cartesia Ink without installing anything?

Yes. AssemblyAI Speech-to-Text (Universal) has a hosted endpoint at https://api.assemblyai.com/v2 and Cartesia Ink at https://api.cartesia.ai.

Other comparisons with AssemblyAI Speech-to-Text (Universal) or Cartesia Ink

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