Cartesia Ink 2 vs Deepgram Flux Multilingual
Deepgram Flux Multilingual 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 (2.57 points lower). Pick Deepgram Flux Multilingual for showing words while the caller is still talking (718ms sooner) and quick turn-taking once the caller stops (9ms 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 Flux Multilingual
- 4.96%16th
Cartesia Ink 2, 2.57 points lower
- Cartesia Ink 2
- 3.09%2nd
- Deepgram Flux Multilingual
- 4.53%15th
Too close to call: inside the margin of error
- Cartesia Ink 2
- 1.51s11th
- Deepgram Flux Multilingual
- 793ms4th
Deepgram Flux Multilingual, 718ms sooner
- Cartesia Ink 2
- 123ms7th
- Deepgram Flux Multilingual
- 114ms6th
Deepgram Flux Multilingual, 9ms 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 Flux Multilingual shows first text after 3.41s and final text after 141ms, 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 Flux Multilingual | 793ms | 2.00s | 3.41s | |
| Final-text delay | Cartesia Ink 2 | 123ms | 139ms | 145ms |
| Deepgram Flux Multilingual | 114ms | 135ms | 141ms |
- 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 | Flux Multilingual |
|---|---|---|
| Pipecat Dataset WER | 2.39%6th of 17 | 4.96%16th of 17 |
| Ocular Dataset WER | 3.09%2nd of 17 | 4.53%15th of 17 |
| Time to first text | 1.51s11th of 15 | 793ms4th of 15 |
| Final-text delay | 123ms7th of 17 | 114ms6th 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 Flux Multilingual | 999 | 8 | 175 | 31 |
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 Gradium
- Deepgram Flux Multilingual vs Deepgram Flux English
- Deepgram Flux Multilingual vs GPT-4o Transcribe
- Deepgram Flux Multilingual vs Smallest Pulse
- Deepgram Flux Multilingual vs Deepgram Nova-3
- Deepgram Flux Multilingual vs Gradium
- Deepgram Flux Multilingual vs GPT-4o Mini Transcribe
- Deepgram Flux Multilingual vs Inworld STT-1
- Deepgram Flux Multilingual vs Soniox STT-RT v5
- Deepgram Flux Multilingual vs Speechmatics Linden
- Deepgram Flux Multilingual vs GPT Realtime Whisper
- Deepgram Flux Multilingual vs Reson8
- Deepgram Flux Multilingual vs Google Chirp 3
- Deepgram Flux Multilingual vs AssemblyAI Universal 3.6 Pro
Frequently asked questions
Which is more accurate, Cartesia Ink 2 or Deepgram Flux Multilingual?
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 Flux Multilingual 4.96%, so Cartesia Ink 2 makes fewer errors by 2.57 points. On the eight licensed Ocular recordings, Cartesia Ink 2 scores 3.09% and Deepgram Flux Multilingual 4.53%, with likely ranges of 2.43 to 3.84% and 3.29 to 5.69%. 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 Flux Multilingual?
No. Deepgram Flux Multilingual finishes the transcript 9ms sooner. Cartesia Ink 2 has the final transcript 123ms after the speaker stops and Deepgram Flux Multilingual 114ms, at the median. Both are measured on the same 206 streamed turns.
Is Cartesia Ink 2 or Deepgram Flux Multilingual better for voice agents?
Deepgram Flux Multilingual finishes the transcript 9ms 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 Flux Multilingual 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 Flux Multilingual after 793ms, at the median, so Deepgram Flux Multilingual is 718ms sooner.