Gradium vs Smallest Pulse
Smallest Pulse is ahead of Gradium on all four metrics.
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
- Smallest Pulse
- 3.66%11th
Smallest Pulse, 2.82 points lower
Word error rate on eight licensed recordings provided by Ocular.
- Gradium
- 4.45%11th
- Smallest Pulse
- 3.46%3rd
Smallest Pulse, 1.00 points lower
Median delay before the first words arrive, from the first audio packet.
- Gradium
- 1.71s10th
- Smallest Pulse
- 1.06s4th
Smallest Pulse, 648ms sooner
Median delay after the speaker stops before the transcript is final.
- Gradium
- 212ms9th
- Smallest Pulse
- 201ms8th
Smallest Pulse, 11ms 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 |
| Smallest Pulse | 1.06s | 2.25s | 3.03s | |
| Final-text delay | Gradium | 212ms | 266ms | 280ms |
| Smallest Pulse | 201ms | 356ms | 773ms |
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 | Speechmatics Linden | 3.93% | 8 | |
| 7 | Deepgram Flux English | 4.18% | 8 | |
| 8 | Google Chirp 3 | 4.19% | 8 | |
| 9 | AssemblyAI Universal 3.5 Pro | 4.23% | 8 | |
| 10 | Deepgram Nova-3 | 4.39% | 8 | |
| 11 | Gradium | 4.45% | 8 | |
| 12 | GPT-4o Mini Transcribe | 4.45% | 8 | |
| 13 | Deepgram Flux Multilingual | 4.53% | 8 | |
| 14 | Inworld STT-1 | 10.60% | 8 | |
| 15 | 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 |
|---|---|---|---|---|
| Gradium | 1,000 | 8 | 198 | 0 |
| Smallest Pulse | 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 Smallest Pulse more accurate?
On the 1,000 public Pipecat clips, Gradium scores 6.48% and Smallest Pulse 3.66%, so Smallest Pulse makes fewer errors by 2.82 points. On the eight licensed Ocular recordings, Gradium scores 4.45% and Smallest Pulse 3.46%, so Smallest Pulse makes fewer errors by 1.00 points. Word error rate counts incorrect, missing, and extra words against the reference transcript, so lower is better.
Which is faster, Gradium or Smallest Pulse?
Smallest Pulse returns first text 648ms sooner, at 1.06s against 1.71s at the median. Smallest Pulse has the final transcript 11ms sooner, 201ms after the speaker stops against 212ms. Both are measured on the same 206 streamed turns.
How were Gradium and Smallest Pulse 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 Smallest Pulse for 1,000. Latency uses each provider's own supported finalization contract.