OpenAICartesiaAudio matchupSpeech to text
GPT-Realtime-Whispervs.Cartesia Ink-2
Which model is better?
Cartesia Ink-2 is slightly ahead in independent tests, but the lead is not certain.
Pick GPT-Realtime-Whisper for
Pick Cartesia Ink-2 for
Shared tests
Independent evaluators and leaderboards only, the newest shared snapshot per evaluator. With 95 % ranges a lead counts when they do not overlap; for hit rates, when it holds in a 95 % test. Without any uncertainty figure at most “slightly ahead”.
Coval
Cartesia Ink-2 slightly aheadCartesia Ink-2 is clearly ahead in 0 of 16 subtests and slightly in 10, GPT-Realtime-Whisper in 0 clearly and slightly in 5. 1 is level.
Coval Time to Final Segment (TTFS) p50
lower is better, as of November 5, 2026
Coval Time to Final Segment (TTFS) mean
lower is better, as of November 5, 2026
Coval Time to First Token (TTFT) maximum
lower is better, as of November 5, 2026
Show all 16 subtests
| Subtest | GPT-Realtime-Whisper | Cartesia Ink-2 | Verdict |
|---|---|---|---|
| Coval Time to Final Segment (TTFS) p50 (lower is better) | 547 ms | 139 ms | Cartesia Ink-2 slightly ahead |
| Coval Time to Final Segment (TTFS) mean (lower is better) | 564 ms | 145 ms | Cartesia Ink-2 slightly ahead |
| Coval Time to First Token (TTFT) maximum (lower is better) | 10,968 ms | 25,200 ms | GPT-Realtime-Whisper slightly ahead |
| Coval Time to Final Segment (TTFS) maximum (lower is better) | 20,386 ms | 31,136 ms | GPT-Realtime-Whisper slightly ahead |
| Coval Word Error Rate (WER) per-sample maximum (lower is better) | 100.0 % | 69.0 % | Cartesia Ink-2 slightly ahead |
| Coval AudioToFinal maximum (lower is better) | 30.01 s | 39.52 s | GPT-Realtime-Whisper slightly ahead |
| Coval RTF maximum (lower is better) | 5.55 | 4.71 | Cartesia Ink-2 slightly ahead |
| Coval Word Error Rate (WER) per-sample mean (lower is better) | 4.5 % | 3.9 % | Cartesia Ink-2 slightly ahead |
| Coval pooled corpus Word Error Rate (WER) (lower is better) | 4.0 % | 3.4 % | Cartesia Ink-2 slightly ahead |
| Coval Time to First Token (TTFT) mean (lower is better) | 1,820 ms | 2,033 ms | GPT-Realtime-Whisper slightly ahead |
| Coval Time to First Token (TTFT) p50 (lower is better) | 1,878 ms | 2,017 ms | GPT-Realtime-Whisper slightly ahead |
| Coval RTF mean (lower is better) | 1.09 | 1.02 | Cartesia Ink-2 slightly ahead |
| Coval AudioToFinal mean (lower is better) | 8.51 s | 8.09 s | Cartesia Ink-2 slightly ahead |
| Coval AudioToFinal p50 (lower is better) | 8.88 s | 8.46 s | Cartesia Ink-2 slightly ahead |
| Coval RTF p50 (lower is better) | 1.07 | 1.02 | Cartesia Ink-2 slightly ahead |
| Coval Word Error Rate (WER) per-sample p50 (lower is better) | 0.0 % | 0.0 % | level |
Source · latest November 5, 2026
All data side by side
Prices are verbatim from the provider, because audio models bill per minute, character or token.
| GPT-Realtime-Whisper | Cartesia Ink-2 | |
|---|---|---|
| Task | Speech to text | Speech to text |
| Developer | OpenAI | Cartesia |
| Status | Active | Active |
| Released | n/a | July 9, 2026 |
| Weights | proprietary | proprietary |
| Runs locally | no | no |
| Price | $0.017 per audio minute | 3 credits per second of audio; the dollar price and overage charges depend on the plan |
| Popularity (out of 100) | 34 | 0 |