Deepgram Flux English vs Deepgram Nova-3
Deepgram Flux English is ahead on the Ocular Dataset and time to first text, and Deepgram Nova-3 on the Pipecat Dataset and 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.
- Deepgram Flux English
- 3.90%13th
- Deepgram Nova-3
- 3.46%10th
Deepgram Nova-3, 0.44 points lower
Word error rate on eight licensed recordings provided by Ocular.
- Deepgram Flux English
- 4.18%7th
- Deepgram Nova-3
- 4.39%10th
Deepgram Flux English, 0.21 points lower
Median delay before the first words arrive, from the first audio packet.
- Deepgram Flux English
- 791ms2nd
- Deepgram Nova-3
- 1.06s6th
Deepgram Flux English, 273ms sooner
Median delay after the speaker stops before the transcript is final.
- Deepgram Flux English
- 108ms3rd
- Deepgram Nova-3
- 103ms2nd
Deepgram Nova-3, 5ms 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 | Deepgram Flux English | 791ms | 1.23s | 1.51s |
| Deepgram Nova-3 | 1.06s | 1.10s | 2.07s | |
| Final-text delay | Deepgram Flux English | 108ms | 132ms | 141ms |
| Deepgram Nova-3 | 103ms | 143ms | 155ms |
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 |
|---|---|---|---|---|
| Deepgram Flux English | 999 | 8 | 199 | 7 |
| Deepgram Nova-3 | 1,000 | 8 | 202 | 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 Deepgram Flux English or Deepgram Nova-3 more accurate?
On the 1,000 public Pipecat clips, Deepgram Flux English scores 3.90% and Deepgram Nova-3 3.46%, so Deepgram Nova-3 makes fewer errors by 0.44 points. On the eight licensed Ocular recordings, Deepgram Flux English scores 4.18% and Deepgram Nova-3 4.39%, so Deepgram Flux English makes fewer errors by 0.21 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, Deepgram Flux English or Deepgram Nova-3?
Deepgram Flux English returns first text 273ms sooner, at 791ms against 1.06s at the median. Deepgram Nova-3 has the final transcript 5ms sooner, 103ms after the speaker stops against 108ms. Both are measured on the same 206 streamed turns.
How were Deepgram Flux English and Deepgram Nova-3 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. Deepgram Flux English returned usable text for 999 of the public clips and Deepgram Nova-3 for 1,000. Latency uses each provider's own supported finalization contract.