GPT Realtime Whisper
GPT Realtime Whisper is 4th of 15 on the Pipecat Dataset and 12th of 15 on final-text delay.
- 2.16%
- Pipecat WER · 4th
- 3.53%
- Ocular WER · 4th
- 1.38s
- First text · 8th
- 543ms
- Final text · 12th
Quality and speed frontier
Every model's error rate on the public clips, against how long its transcript takes to settle.
GPT Realtime Whisper against every other model
Open on the metric GPT Realtime Whisper places highest on, with the other three a tab away. Lower is better on all of them, so the order runs best first.
Word error rate on 1,000 clips from Pipecat's STT benchmark dataset. Lower is better.
| # | Model | Pipecat Dataset | clips | |
|---|---|---|---|---|
| 1 | AssemblyAI Universal 3.5 Pro | 1.93% | 1,000 | |
| 2 | Google Chirp 3 | 2.00% | 1,000 | |
| 3 | Reson8 | 2.10% | 1,000 | |
| 4 | GPT Realtime Whisper | 2.16% | 1,000 | |
| 5 | Cartesia Ink 2 | 2.39% | 1,000 | |
| 6 | Speechmatics Linden | 2.46% | 998 | |
| 7 | Google Chirp 2 | 2.59% | 1,000 | |
| 8 | Inworld STT-1 | 2.72% | 1,000 | |
| 9 | GPT-4o Mini Transcribe | 3.35% | 1,000 | |
| 10 | Deepgram Nova-3 | 3.46% | 1,000 | |
| 11 | Smallest Pulse | 3.66% | 1,000 | |
| 12 | GPT-4o Transcribe | 3.90% | 1,000 | |
| 13 | Deepgram Flux English | 3.90% | 999 | |
| 14 | Deepgram Flux Multilingual | 4.96% | 999 | |
| 15 | Gradium | 6.48% | 1,000 |
Counts are the clips each model returned usable text for, so they differ between models and between datasets.
First text and final text, at three percentiles
Measured on the same 206 streamed Ocular Dataset turns as every other model. P90 and P95 say what a caller meets on a bad turn, which a median hides.
| Measure | P50 | P90 | P95 |
|---|---|---|---|
| Time to first text | 1.38s | 1.84s | 2.86s |
| Final-text delay | 543ms | 647ms | 669ms |
GPT Realtime Whisper on the other two views
The same charts the benchmark page carries, with GPT Realtime Whisper ringed. Consistency across the two datasets is one reading; how fast a model starts against how fast it commits is the other.
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
- 1,000
- Pipecat clips scored
- 8
- Ocular recordings scored
- 206
- turns timed
- 0
- requests that failed
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
Where does GPT Realtime Whisper place in the benchmark?
GPT Realtime Whisper places highest on the Pipecat Dataset, 4th of 15 at 2.16%. Its weakest placing is final-text delay, 12th of 15 at 543ms.
How accurate is GPT Realtime Whisper?
GPT Realtime Whisper transcribes the 1,000 public Pipecat clips at 2.16% word error rate and the eight licensed Ocular recordings at 3.53%. Word error rate counts incorrect, missing, and extra words against the reference transcript, so lower is better.
How fast is GPT Realtime Whisper in a live conversation?
First text arrives after 1.38s at the median, and the transcript is final 543ms after the speaker stops. Both are measured on the same 206 streamed turns as every other model, and the page shows P90 and P95 as well, which is what a caller meets on a bad turn.
How was GPT Realtime Whisper measured?
Every model runs the same two datasets under the same conditions: 1,000 public clips from Pipecat's STT benchmark dataset for accuracy at scale, and eight licensed conversation recordings from Ocular for real speech. Latency comes from 206 streamed turns, using each provider's own supported finalization contract. GPT Realtime Whisper returned usable text for 1,000 of the public clips.