AssemblyAI Universal 3.6 Pro vs Cartesia Ink 2
AssemblyAI Universal 3.6 Pro is ahead on the Pipecat Dataset, time to first text and final-text delay, and Cartesia Ink 2 on the Ocular Dataset.
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.
- AssemblyAI Universal 3.6 Pro
- 1.77%1st
- Cartesia Ink 2
- 2.39%6th
AssemblyAI Universal 3.6 Pro, 0.62 points lower
Word error rate on eight licensed recordings provided by Ocular.
- AssemblyAI Universal 3.6 Pro
- 4.50%14th
- Cartesia Ink 2
- 3.09%2nd
Cartesia Ink 2, 1.41 points lower
Median delay before the first words arrive, from the first audio packet.
- AssemblyAI Universal 3.6 Pro
- 485ms1st
- Cartesia Ink 2
- 1.51s11th
AssemblyAI Universal 3.6 Pro, 1.03s sooner
Median delay after the speaker stops before the transcript is final.
- AssemblyAI Universal 3.6 Pro
- 91ms3rd
- Cartesia Ink 2
- 123ms7th
AssemblyAI Universal 3.6 Pro, 32ms 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 | AssemblyAI Universal 3.6 Pro | 485ms | 966ms | 967ms |
| Cartesia Ink 2 | 1.51s | 2.04s | 3.23s | |
| Final-text delay | AssemblyAI Universal 3.6 Pro | 91ms | 210ms | 232ms |
| Cartesia Ink 2 | 123ms | 139ms | 145ms |
Both against every other model
Open on the metric where the two sit furthest apart, with the other three a tab away.
Word error rate on eight licensed recordings provided by Ocular. Lower is better.
| # | Model | Ocular Dataset | clips | |
|---|---|---|---|---|
| 1 | Reson8 | 2.93% | 8 | |
| 2 | Cartesia Ink 2 | 3.09% | 8 | |
| 3 | Smallest Pulse | 3.46% | 8 | |
| 4 | GPT Realtime Whisper | 3.53% | 8 | |
| 5 | Google Chirp 2 | 3.80% | 8 | |
| 6 | Soniox STT-RT v5 | 3.92% | 8 | |
| 7 | Speechmatics Linden | 3.93% | 8 | |
| 8 | Deepgram Flux English | 4.18% | 8 | |
| 9 | Google Chirp 3 | 4.19% | 8 | |
| 10 | AssemblyAI Universal 3.5 Pro | 4.23% | 8 | |
| 11 | Deepgram Nova-3 | 4.39% | 8 | |
| 12 | Gradium | 4.45% | 8 | |
| 13 | GPT-4o Mini Transcribe | 4.45% | 8 | |
| 14 | AssemblyAI Universal 3.6 Pro | 4.50% | 8 | |
| 15 | Deepgram Flux Multilingual | 4.53% | 8 | |
| 16 | Inworld STT-1 | 10.60% | 8 | |
| 17 | GPT-4o Transcribe | 12.45% | 8 |
Counts are the clips each model returned usable text for, so they differ between models and between datasets.
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 |
|---|---|---|---|---|
| AssemblyAI Universal 3.6 Pro | 1,000 | 8 | 206 | 0 |
| Cartesia Ink 2 | 1,000 | 8 | 198 | 0 |
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 AssemblyAI Universal 3.6 Pro or Cartesia Ink 2 more accurate?
On the 1,000 public Pipecat clips, AssemblyAI Universal 3.6 Pro scores 1.77% and Cartesia Ink 2 2.39%, so AssemblyAI Universal 3.6 Pro makes fewer errors by 0.62 points. On the eight licensed Ocular recordings, AssemblyAI Universal 3.6 Pro scores 4.50% and Cartesia Ink 2 3.09%, so Cartesia Ink 2 makes fewer errors by 1.41 points. The two datasets disagree, so the better choice depends on whether your audio looks more like clean public clips or real conversations.
Which is faster, AssemblyAI Universal 3.6 Pro or Cartesia Ink 2?
AssemblyAI Universal 3.6 Pro returns first text 1.03s sooner, at 485ms against 1.51s at the median. AssemblyAI Universal 3.6 Pro has the final transcript 32ms sooner, 91ms after the speaker stops against 123ms. Both are measured on the same 206 streamed turns.
How were AssemblyAI Universal 3.6 Pro and Cartesia Ink 2 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. AssemblyAI Universal 3.6 Pro returned usable text for 1,000 of the public clips and Cartesia Ink 2 for 1,000. Latency uses each provider's own supported finalization contract.