Gradium vs GPT Realtime Whisper
GPT Realtime Whisper is ahead on the Pipecat Dataset, the Ocular Dataset and time to first text, and Gradium on 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.
- Gradium
- 6.48%15th
- GPT Realtime Whisper
- 2.16%4th
GPT Realtime Whisper, 4.32 points lower
Word error rate on eight licensed recordings provided by Ocular.
- Gradium
- 4.45%11th
- GPT Realtime Whisper
- 3.53%4th
GPT Realtime Whisper, 0.92 points lower
Median delay before the first words arrive, from the first audio packet.
- Gradium
- 1.71s10th
- GPT Realtime Whisper
- 1.38s8th
GPT Realtime Whisper, 326ms sooner
Median delay after the speaker stops before the transcript is final.
- Gradium
- 212ms9th
- GPT Realtime Whisper
- 543ms12th
Gradium, 331ms 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 | Gradium | 1.71s | 4.05s | 7.32s |
| GPT Realtime Whisper | 1.38s | 1.84s | 2.86s | |
| Final-text delay | Gradium | 212ms | 266ms | 280ms |
| GPT Realtime Whisper | 543ms | 647ms | 669ms |
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 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.
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 |
|---|---|---|---|---|
| Gradium | 1,000 | 8 | 198 | 0 |
| GPT Realtime Whisper | 1,000 | 8 | 206 | 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 Gradium or GPT Realtime Whisper more accurate?
On the 1,000 public Pipecat clips, Gradium scores 6.48% and GPT Realtime Whisper 2.16%, so GPT Realtime Whisper makes fewer errors by 4.32 points. On the eight licensed Ocular recordings, Gradium scores 4.45% and GPT Realtime Whisper 3.53%, so GPT Realtime Whisper makes fewer errors by 0.92 points. Word error rate counts incorrect, missing, and extra words against the reference transcript, so lower is better.
Which is faster, Gradium or GPT Realtime Whisper?
GPT Realtime Whisper returns first text 326ms sooner, at 1.38s against 1.71s at the median. Gradium has the final transcript 331ms sooner, 212ms after the speaker stops against 543ms. Both are measured on the same 206 streamed turns.
How were Gradium and GPT Realtime Whisper 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. Gradium returned usable text for 1,000 of the public clips and GPT Realtime Whisper for 1,000. Latency uses each provider's own supported finalization contract.