AssemblyAI Universal 3.6 Pro vs Gradium
AssemblyAI Universal 3.6 Pro is ahead on the Pipecat Dataset, time to first text and final-text delay, and Gradium on the Ocular Dataset.
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.
- AssemblyAI Universal 3.6 Pro
- 1.77%1st
- Gradium
- 6.48%17th
AssemblyAI Universal 3.6 Pro, 4.71 points lower
Word error rate on eight licensed recordings provided by Ocular.
- AssemblyAI Universal 3.6 Pro
- 4.50%14th
- Gradium
- 4.45%12th
Gradium, 0.05 points lower
Median delay before the first words arrive, from the first audio packet.
- AssemblyAI Universal 3.6 Pro
- 485ms1st
- Gradium
- 1.71s12th
AssemblyAI Universal 3.6 Pro, 1.22s sooner
Median delay after the speaker stops before the transcript is final.
- AssemblyAI Universal 3.6 Pro
- 91ms3rd
- Gradium
- 212ms11th
AssemblyAI Universal 3.6 Pro, 121ms 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 | AssemblyAI Universal 3.6 Pro | 485ms | 966ms | 967ms |
| Gradium | 1.71s | 4.05s | 7.32s | |
| Final-text delay | AssemblyAI Universal 3.6 Pro | 91ms | 210ms | 232ms |
| Gradium | 212ms | 266ms | 280ms |
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 3.6 Pro | 1.77% | 1,000 | |
| 2 | AssemblyAI Universal 3.5 Pro | 1.93% | 1,000 | |
| 3 | Google Chirp 3 | 2.00% | 1,000 | |
| 4 | Reson8 | 2.10% | 1,000 | |
| 5 | GPT Realtime Whisper | 2.16% | 1,000 | |
| 6 | Cartesia Ink 2 | 2.39% | 1,000 | |
| 7 | Speechmatics Linden | 2.46% | 998 | |
| 8 | Soniox STT-RT v5 | 2.54% | 1,000 | |
| 9 | Google Chirp 2 | 2.59% | 1,000 | |
| 10 | Inworld STT-1 | 2.72% | 1,000 | |
| 11 | GPT-4o Mini Transcribe | 3.35% | 1,000 | |
| 12 | Deepgram Nova-3 | 3.46% | 1,000 | |
| 13 | Smallest Pulse | 3.66% | 1,000 | |
| 14 | GPT-4o Transcribe | 3.90% | 1,000 | |
| 15 | Deepgram Flux English | 3.90% | 999 | |
| 16 | Deepgram Flux Multilingual | 4.96% | 999 | |
| 17 | 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 |
|---|---|---|---|---|
| AssemblyAI Universal 3.6 Pro | 1,000 | 8 | 206 | 0 |
| Gradium | 1,000 | 8 | 198 | 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 AssemblyAI Universal 3.6 Pro or Gradium more accurate?
On the 1,000 public Pipecat clips, AssemblyAI Universal 3.6 Pro scores 1.77% and Gradium 6.48%, so AssemblyAI Universal 3.6 Pro makes fewer errors by 4.71 points. On the eight licensed Ocular recordings, AssemblyAI Universal 3.6 Pro scores 4.50% and Gradium 4.45%, so Gradium makes fewer errors by 0.05 points. The two datasets disagree, so the better choice depends on whether your audio looks more like clean public clips or real conversations.
Which is faster, AssemblyAI Universal 3.6 Pro or Gradium?
AssemblyAI Universal 3.6 Pro returns first text 1.22s sooner, at 485ms against 1.71s at the median. AssemblyAI Universal 3.6 Pro has the final transcript 121ms sooner, 91ms after the speaker stops against 212ms. Both are measured on the same 206 streamed turns.
How were AssemblyAI Universal 3.6 Pro and Gradium 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. AssemblyAI Universal 3.6 Pro returned usable text for 1,000 of the public clips and Gradium for 1,000. Latency uses each provider's own supported finalization contract.