Cartesia Ink 2 vs Deepgram Flux English
Cartesia Ink 2 is ahead on the Pipecat Dataset and the Ocular Dataset, and Deepgram Flux English on time to first text and final-text delay.
Quality and speed frontier
Every model's error rate on the public clips, against how long its transcript takes to settle.
The four metrics, side by side
Word error rate on 1,000 clips from Pipecat's STT benchmark dataset.
- Cartesia Ink 2
- 2.39%5th
- Deepgram Flux English
- 3.90%13th
Cartesia Ink 2, 1.52 points lower
Word error rate on eight licensed recordings provided by Ocular.
- Cartesia Ink 2
- 3.09%2nd
- Deepgram Flux English
- 4.18%7th
Cartesia Ink 2, 1.09 points lower
Median delay before the first words arrive, from the first audio packet.
- Cartesia Ink 2
- 1.51s9th
- Deepgram Flux English
- 791ms2nd
Deepgram Flux English, 720ms sooner
Median delay after the speaker stops before the transcript is final.
- Cartesia Ink 2
- 123ms5th
- Deepgram Flux English
- 108ms3rd
Deepgram Flux English, 15ms sooner
Lower is better on every metric. The small figure is each model's place in the whole field.
First text and final text, at three percentiles
Both measured on the same 206 streamed Ocular Dataset turns. P90 and P95 say what a caller meets on a bad turn, which a median hides.
| Measure | Model | P50 | P90 | P95 |
|---|---|---|---|---|
| Time to first text | Cartesia Ink 2 | 1.51s | 2.04s | 3.23s |
| Deepgram Flux English | 791ms | 1.23s | 1.51s | |
| Final-text delay | Cartesia Ink 2 | 123ms | 139ms | 145ms |
| Deepgram Flux English | 108ms | 132ms | 141ms |
Both against every other model
Open on the metric where the two sit furthest apart, with the other three a tab away.
Time to first text, measured from the first audio packet. Lower is better.
| # | Model | First text | turns | |
|---|---|---|---|---|
| 1 | AssemblyAI Universal 3.5 Pro | 489ms | 205 | |
| 2 | Deepgram Flux English | 791ms | 199 | |
| 3 | Deepgram Flux Multilingual | 793ms | 175 | |
| 4 | Smallest Pulse | 1057ms | 206 | |
| 5 | Inworld STT-1 | 1063ms | 206 | |
| 6 | Deepgram Nova-3 | 1064ms | 203 | |
| 7 | Speechmatics Linden | 1190ms | 194 | |
| 8 | GPT Realtime Whisper | 1379ms | 206 | |
| 9 | Cartesia Ink 2 | 1511ms | 198 | |
| 10 | Gradium | 1705ms | 198 | |
| 11 | Reson8 | 2400ms | 201 | |
| 12 | Google Chirp 3 | 4480ms | 206 | |
| 13 | Google Chirp 2 | 4497ms | 205 |
Not ranked: GPT-4o Mini Transcribe and GPT-4o Transcribe return no text until the speaker stops, so first-text time is not comparable.
Median across the same 206 Ocular Dataset turns. Providers finalize differently, so compare models with similar finalization contracts before treating small gaps as meaningful.
Both on the other two views
Pipecat vs Ocular accuracy
Every model's error rate on the public clips, against the same model on real conversations.
Transcription response time
How soon each model returns its first words, against how soon its transcript is final.
What the numbers rest on
| Model | Pipecat clips | Ocular recordings | Turns timed | Failed |
|---|---|---|---|---|
| Cartesia Ink 2 | 1,000 | 8 | 198 | 0 |
| Deepgram Flux English | 999 | 8 | 199 | 7 |
A clip counts only where the model returned usable text, so counts differ between models. Word error rate is measured the same way throughout: incorrect, missing, and extra words against the reference transcript.
Frequently asked questions
Is Cartesia Ink 2 or Deepgram Flux English more accurate?
On the 1,000 public Pipecat clips, Cartesia Ink 2 scores 2.39% and Deepgram Flux English 3.90%, so Cartesia Ink 2 makes fewer errors by 1.52 points. On the eight licensed Ocular recordings, Cartesia Ink 2 scores 3.09% and Deepgram Flux English 4.18%, so Cartesia Ink 2 makes fewer errors by 1.09 points. Word error rate counts incorrect, missing, and extra words against the reference transcript, so lower is better.
Which is faster, Cartesia Ink 2 or Deepgram Flux English?
Deepgram Flux English returns first text 720ms sooner, at 791ms against 1.51s at the median. Deepgram Flux English has the final transcript 15ms sooner, 108ms after the speaker stops against 123ms. Both are measured on the same 206 streamed turns.
How were Cartesia Ink 2 and Deepgram Flux English compared?
Both ran the same two datasets under the same conditions as every other model in the benchmark: 1,000 public clips from Pipecat's STT benchmark dataset and eight licensed conversation recordings from Ocular. Cartesia Ink 2 returned usable text for 1,000 of the public clips and Deepgram Flux English for 999. Latency uses each provider's own supported finalization contract.