Cartesia Ink 2 vs GPT-4o Transcribe
Cartesia Ink 2 is ahead of GPT-4o Transcribe on the Pipecat Dataset, the Ocular Dataset and final-text delay.
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 GPT-4o Transcribe on every measure that separates them: accuracy on clean, scripted audio (1.52 points lower), accuracy on real phone conversations (9.36 points lower) and quick turn-taking once the caller stops (529ms sooner).
The four metrics, side by side
- Cartesia Ink 2
- 2.39%6th
- GPT-4o Transcribe
- 3.90%14th
Cartesia Ink 2, 1.52 points lower
- Cartesia Ink 2
- 3.09%2nd
- GPT-4o Transcribe
- 12.45%17th
Cartesia Ink 2, 9.36 points lower
- Cartesia Ink 2
- 1.51s11th
- GPT-4o Transcribe
- No text until the speaker stops
Not comparable
- Cartesia Ink 2
- 123ms7th
- GPT-4o Transcribe
- 652ms17th
Cartesia Ink 2, 529ms 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 GPT-4o Transcribe shows first text after 40.63s and final text after 1.97s, 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 |
| GPT-4o Transcribe | No text until the speaker stops | |||
| Final-text delay | Cartesia Ink 2 | 123ms | 139ms | 145ms |
| GPT-4o Transcribe | 652ms | 1.73s | 1.97s | |
- 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 | 4o Transcribe |
|---|---|---|
| Pipecat Dataset WER | 2.39%6th of 17 | 3.90%14th of 17 |
| Ocular Dataset WER | 3.09%2nd of 17 | 12.45%17th of 17 |
| Time to first text | 1.51s11th of 15 | Not comparable |
| Final-text delay | 123ms7th of 17 | 652ms17th 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 |
| GPT-4o Transcribe | 1,000 | 8 | 206 | 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 Deepgram Flux English
- Cartesia Ink 2 vs Deepgram Flux Multilingual
- Cartesia Ink 2 vs Gradium
- GPT-4o Transcribe vs Deepgram Flux English
- GPT-4o Transcribe vs Smallest Pulse
- GPT-4o Transcribe vs Deepgram Nova-3
- GPT-4o Transcribe vs GPT-4o Mini Transcribe
- GPT-4o Transcribe vs Deepgram Flux Multilingual
- GPT-4o Transcribe vs Inworld STT-1
- GPT-4o Transcribe vs Soniox STT-RT v5
- GPT-4o Transcribe vs Speechmatics Linden
- GPT-4o Transcribe vs GPT Realtime Whisper
- GPT-4o Transcribe vs Reson8
- GPT-4o Transcribe vs Google Chirp 3
- GPT-4o Transcribe vs AssemblyAI Universal 3.6 Pro
- GPT-4o Transcribe vs Gradium
Frequently asked questions
Which is more accurate, Cartesia Ink 2 or GPT-4o Transcribe?
Cartesia Ink 2 is more accurate on both datasets. On the 1,000 public Pipecat clips, Cartesia Ink 2 scores 2.39% and GPT-4o Transcribe 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 GPT-4o Transcribe 12.45%, so Cartesia Ink 2 makes fewer errors by 9.36 points. Word error rate counts incorrect, missing, and extra words, so lower is better.
Is Cartesia Ink 2 faster than GPT-4o Transcribe?
Yes. Cartesia Ink 2 finishes the transcript 529ms sooner. Cartesia Ink 2 has the final transcript 123ms after the speaker stops and GPT-4o Transcribe 652ms, at the median. Both are measured on the same 206 streamed turns.
Is Cartesia Ink 2 or GPT-4o Transcribe better for voice agents?
Cartesia Ink 2 is the stronger pick for voice agents: it makes fewer errors on real conversations and finishes the transcript 529ms sooner. A voice agent cannot reply until the final transcript arrives, and the Ocular recordings are real conversations.
Do Cartesia Ink 2 and GPT-4o Transcribe stream text while the speaker is talking?
Only Cartesia Ink 2. GPT-4o Transcribe returns no text until the speaker stops, which matters if your agent reacts to partial transcripts.