GPT Realtime Whisper vs Reson8
Reson8 is ahead on the Pipecat Dataset, the Ocular Dataset and final-text delay, and GPT Realtime Whisper on time to first text.
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.
- GPT Realtime Whisper
- 2.16%4th
- Reson8
- 2.10%3rd
Reson8, 0.06 points lower
Word error rate on eight licensed recordings provided by Ocular.
- GPT Realtime Whisper
- 3.53%4th
- Reson8
- 2.93%1st
Reson8, 0.60 points lower
Median delay before the first words arrive, from the first audio packet.
- GPT Realtime Whisper
- 1.38s8th
- Reson8
- 2.40s11th
GPT Realtime Whisper, 1.02s sooner
Median delay after the speaker stops before the transcript is final.
- GPT Realtime Whisper
- 543ms12th
- Reson8
- 235ms10th
Reson8, 308ms 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 | GPT Realtime Whisper | 1.38s | 1.84s | 2.86s |
| Reson8 | 2.40s | 7.97s | 10.20s | |
| Final-text delay | GPT Realtime Whisper | 543ms | 647ms | 669ms |
| Reson8 | 235ms | 357ms | 398ms |
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 |
|---|---|---|---|---|
| GPT Realtime Whisper | 1,000 | 8 | 206 | 0 |
| Reson8 | 1,000 | 8 | 201 | 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 GPT Realtime Whisper or Reson8 more accurate?
On the 1,000 public Pipecat clips, GPT Realtime Whisper scores 2.16% and Reson8 2.10%, so Reson8 makes fewer errors by 0.06 points. On the eight licensed Ocular recordings, GPT Realtime Whisper scores 3.53% and Reson8 2.93%, so Reson8 makes fewer errors by 0.60 points. Word error rate counts incorrect, missing, and extra words against the reference transcript, so lower is better.
Which is faster, GPT Realtime Whisper or Reson8?
GPT Realtime Whisper returns first text 1.02s sooner, at 1.38s against 2.40s at the median. Reson8 has the final transcript 308ms sooner, 235ms after the speaker stops against 543ms. Both are measured on the same 206 streamed turns.
How were GPT Realtime Whisper and Reson8 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. GPT Realtime Whisper returned usable text for 1,000 of the public clips and Reson8 for 1,000. Latency uses each provider's own supported finalization contract.