All tasks / Models
Ink-2
Cartesia's streaming speech-to-text API with built-in turn detection for voice agents.
- Cartesia
- Closed
Where it ranks
- ATranscriptionModels · Cloud · 3.4% on Artificial Analysis Speech to Text: AA-WER Streaming (secondary benchmark)
Facts
- Vendor
- Cartesia
- Family
- Cartesia Ink
- Released
- —
- Weights
- Closed: API and apps only
- License
- proprietary
- API price
- $0.0040 per minute of audio (Artificial Analysis streaming board lists $4.00 per 1,000 minutes (Ink-2); divided by 1,000.)
- Last verified
- 19 Oct 2026
Price from artificialanalysis.ai, 19 Oct 2026.
Benchmark results
| Benchmark | Result | Entry on the leaderboard | As of | Source |
|---|---|---|---|---|
| Artificial Analysis Speech to Text: AA-WER Streaming | 3.4% | Cartesia Ink-2 (semantic endpoints)AA-WER Streaming index (final transcripts), provider Cartesia; embedded value 0.033612 converted to percent and rounded; page shows no last-updated date. | 19 Oct 2026 | artificialanalysis.ai |
| Coval Benchmarks: Speech-to-Text WER (24h window) | 3.5% | cartesia / ink-2Coval STT benchmark, mean WER over the trailing 24h window (snapshot generation 2610, as_of 2026-10-19T09:38Z), n=912 clips; rank 8 of 31; read from the public API that feeds https://benchmarks.coval.ai. | 19 Oct 2026 | benchmarks-api-6wxgp27p2a-ue.a.run.app |
Where you can use it
No tracked tool lists this model yet.