Cartesia Ink 2 vs Gradium
Cartesia Ink 2 is ahead of Gradium on the Pipecat Dataset, time to first text and final-text delay. The Ocular Dataset is too close to call.
Last updated Methodology by Dileep Chagam
Accuracy vs speed
Each dot is one model. Bottom-left is best: fewer errors and a faster final transcript.
Which to pick
Cartesia Ink 2 is the better pick over Gradium on every measure that separates them: accuracy on clean, scripted audio (4.09 points lower), showing words while the caller is still talking (194ms sooner) and quick turn-taking once the caller stops (89ms sooner). For accuracy on real phone conversations, the gap is inside the margin of error, so neither is ahead.
The four metrics, side by side
- Cartesia Ink 2
- 2.39%6th
- Gradium
- 6.48%17th
Cartesia Ink 2, 4.09 points lower
- Cartesia Ink 2
- 3.09%2nd
- Gradium
- 4.45%12th
Too close to call: inside the margin of error
- Cartesia Ink 2
- 1.51s11th
- Gradium
- 1.71s12th
Cartesia Ink 2, 194ms sooner
- Cartesia Ink 2
- 123ms7th
- Gradium
- 212ms11th
Cartesia Ink 2, 89ms sooner
Lower is better on every metric. The small figure is each model's place in the whole field. What each metric measures.
- WER · Word error rate
- Share of words the model got wrong: replaced, missing or added. Lower is better.
- Pipecat Dataset
- 1,000 short public clips from Pipecat's STT benchmark dataset.
- Ocular Dataset
- 8 recordings from 4 real phone conversations, licensed from Ocular.
- TTFT · Time to first text
- How long after the audio starts streaming until the first words appear.
- TTFS · Final-text delay
- How long after the caller stops until the full transcript arrives. A voice agent waits for this before it replies.
First text and final text, at three percentiles
Cartesia Ink 2 shows first text after 3.23s and final text after 145ms, and Gradium shows first text after 7.32s and final text after 280ms, on a bad turn (P95) across the same streamed turns.
| Measure | Model | P50 | P90 | P95 |
|---|---|---|---|---|
| Time to first text | Cartesia Ink 2 | 1.51s | 2.04s | 3.23s |
| Gradium | 1.71s | 4.05s | 7.32s | |
| Final-text delay | Cartesia Ink 2 | 123ms | 139ms | 145ms |
| Gradium | 212ms | 266ms | 280ms |
- P50 / P90 / P95 · Typical, slow and slowest turns
- Half of turns are faster than P50. Only 1 in 10 is slower than P90, and 1 in 20 slower than P95.
How each ranks among all 17 models
Place among the 17 models on each metric. Lower is better on all four.
| Metric | Ink 2 | Gradium |
|---|---|---|
| Pipecat Dataset WER | 2.39%6th of 17 | 6.48%17th of 17 |
| Ocular Dataset WER | 3.09%2nd of 17 | 4.45%12th of 17 |
| Time to first text | 1.51s11th of 15 | 1.71s12th of 15 |
| Final-text delay | 123ms7th of 17 | 212ms11th of 17 |
How much audio each model was tested on
| Model | Pipecat clips | Ocular recordings | Turns timed | Failed |
|---|---|---|---|---|
| Cartesia Ink 2 | 1,000 | 8 | 198 | 0 |
| Gradium | 1,000 | 8 | 198 | 0 |
Only clips with usable text count, so the two totals can differ. How WER is scored.
Related comparisons
- Cartesia Ink 2 vs Speechmatics Linden
- Cartesia Ink 2 vs Soniox STT-RT v5
- Cartesia Ink 2 vs GPT Realtime Whisper
- Cartesia Ink 2 vs Reson8
- Cartesia Ink 2 vs Inworld STT-1
- Cartesia Ink 2 vs Google Chirp 3
- Cartesia Ink 2 vs AssemblyAI Universal 3.6 Pro
- Cartesia Ink 2 vs GPT-4o Mini Transcribe
- Cartesia Ink 2 vs Deepgram Nova-3
- Cartesia Ink 2 vs Smallest Pulse
- Cartesia Ink 2 vs GPT-4o Transcribe
- Cartesia Ink 2 vs Deepgram Flux English
- Cartesia Ink 2 vs Deepgram Flux Multilingual
- Gradium vs Deepgram Flux Multilingual
- Gradium vs Deepgram Flux English
- Gradium vs GPT-4o Transcribe
- Gradium vs Smallest Pulse
- Gradium vs Deepgram Nova-3
- Gradium vs GPT-4o Mini Transcribe
- Gradium vs Inworld STT-1
- Gradium vs Soniox STT-RT v5
- Gradium vs Speechmatics Linden
- Gradium vs GPT Realtime Whisper
- Gradium vs Reson8
- Gradium vs Google Chirp 3
- Gradium vs AssemblyAI Universal 3.6 Pro
Frequently asked questions
Which is more accurate, Cartesia Ink 2 or Gradium?
Cartesia Ink 2 is more accurate on the public clips. On the 1,000 public Pipecat clips, Cartesia Ink 2 scores 2.39% and Gradium 6.48%, so Cartesia Ink 2 makes fewer errors by 4.09 points. On the eight licensed Ocular recordings, Cartesia Ink 2 scores 3.09% and Gradium 4.45%, with likely ranges of 2.43 to 3.84% and 3.17 to 5.90%. The ranges overlap, so the difference is too close to call. Word error rate counts incorrect, missing, and extra words, so lower is better.
Is Cartesia Ink 2 faster than Gradium?
Yes. Cartesia Ink 2 finishes the transcript 89ms sooner. Cartesia Ink 2 has the final transcript 123ms after the speaker stops and Gradium 212ms, at the median. Both are measured on the same 206 streamed turns.
Is Cartesia Ink 2 or Gradium better for voice agents?
Cartesia Ink 2 finishes the transcript 89ms sooner, and the two are too close to call on real conversations. A voice agent cannot reply until the final transcript arrives, and the Ocular recordings are real conversations.
Do Cartesia Ink 2 and Gradium stream text while the speaker is talking?
Yes, both return partial text before the speaker stops. Cartesia Ink 2 shows first text after 1.51s and Gradium after 1.71s, at the median, so Cartesia Ink 2 is 194ms sooner.