Cartesia Ink 2 vs Deepgram Nova-3
Deepgram Nova-3 is ahead on time to first text and final-text delay, and Cartesia Ink 2 on the Pipecat Dataset. 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
Pick Cartesia Ink 2 for accuracy on clean, scripted audio (1.08 points lower). Pick Deepgram Nova-3 for showing words while the caller is still talking (447ms sooner) and quick turn-taking once the caller stops (20ms 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
- Deepgram Nova-3
- 3.46%12th
Cartesia Ink 2, 1.08 points lower
- Cartesia Ink 2
- 3.09%2nd
- Deepgram Nova-3
- 4.39%11th
Too close to call: inside the margin of error
- Cartesia Ink 2
- 1.51s11th
- Deepgram Nova-3
- 1.06s7th
Deepgram Nova-3, 447ms sooner
- Cartesia Ink 2
- 123ms7th
- Deepgram Nova-3
- 103ms4th
Deepgram Nova-3, 20ms 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 Deepgram Nova-3 shows first text after 2.07s and final text after 155ms, 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 |
| Deepgram Nova-3 | 1.06s | 1.10s | 2.07s | |
| Final-text delay | Cartesia Ink 2 | 123ms | 139ms | 145ms |
| Deepgram Nova-3 | 103ms | 143ms | 155ms |
- 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 | Nova-3 |
|---|---|---|
| Pipecat Dataset WER | 2.39%6th of 17 | 3.46%12th of 17 |
| Ocular Dataset WER | 3.09%2nd of 17 | 4.39%11th of 17 |
| Time to first text | 1.51s11th of 15 | 1.06s7th of 15 |
| Final-text delay | 123ms7th of 17 | 103ms4th 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 |
| Deepgram Nova-3 | 1,000 | 8 | 202 | 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 Smallest Pulse
- Cartesia Ink 2 vs GPT-4o Transcribe
- Cartesia Ink 2 vs Deepgram Flux English
- Cartesia Ink 2 vs Deepgram Flux Multilingual
- Cartesia Ink 2 vs Gradium
- Deepgram Nova-3 vs GPT-4o Mini Transcribe
- Deepgram Nova-3 vs Smallest Pulse
- Deepgram Nova-3 vs GPT-4o Transcribe
- Deepgram Nova-3 vs Deepgram Flux English
- Deepgram Nova-3 vs Inworld STT-1
- Deepgram Nova-3 vs Soniox STT-RT v5
- Deepgram Nova-3 vs Speechmatics Linden
- Deepgram Nova-3 vs GPT Realtime Whisper
- Deepgram Nova-3 vs Reson8
- Deepgram Nova-3 vs Google Chirp 3
- Deepgram Nova-3 vs Deepgram Flux Multilingual
- Deepgram Nova-3 vs AssemblyAI Universal 3.6 Pro
- Deepgram Nova-3 vs Gradium
Frequently asked questions
Which is more accurate, Cartesia Ink 2 or Deepgram Nova-3?
Cartesia Ink 2 is more accurate on the public clips. On the 1,000 public Pipecat clips, Cartesia Ink 2 scores 2.39% and Deepgram Nova-3 3.46%, so Cartesia Ink 2 makes fewer errors by 1.08 points. On the eight licensed Ocular recordings, Cartesia Ink 2 scores 3.09% and Deepgram Nova-3 4.39%, with likely ranges of 2.43 to 3.84% and 3.42 to 5.25%. 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 Deepgram Nova-3?
No. Deepgram Nova-3 finishes the transcript 20ms sooner. Cartesia Ink 2 has the final transcript 123ms after the speaker stops and Deepgram Nova-3 103ms, at the median. Both are measured on the same 206 streamed turns.
Is Cartesia Ink 2 or Deepgram Nova-3 better for voice agents?
Deepgram Nova-3 finishes the transcript 20ms 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 Deepgram Nova-3 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 Deepgram Nova-3 after 1.06s, at the median, so Deepgram Nova-3 is 447ms sooner.