Reson8 vs Soniox STT-RT v5
Reson8 is ahead on the Pipecat Dataset and the Ocular Dataset, and Soniox STT-RT v5 on time to first text 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.
- Reson8
- 2.10%4th
- Soniox STT-RT v5
- 2.54%8th
Reson8, 0.45 points lower
Word error rate on eight licensed recordings provided by Ocular.
- Reson8
- 2.93%1st
- Soniox STT-RT v5
- 3.92%6th
Reson8, 1.00 points lower
Median delay before the first words arrive, from the first audio packet.
- Reson8
- 2.40s13th
- Soniox STT-RT v5
- 1.20s9th
Soniox STT-RT v5, 1.21s sooner
Median delay after the speaker stops before the transcript is final.
- Reson8
- 235ms12th
- Soniox STT-RT v5
- 38ms1st
Soniox STT-RT v5, 197ms 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 | Reson8 | 2.40s | 7.97s | 10.20s |
| Soniox STT-RT v5 | 1.20s | 1.67s | 1.71s | |
| Final-text delay | Reson8 | 235ms | 357ms | 398ms |
| Soniox STT-RT v5 | 38ms | 72ms | 79ms |
Both against every other model
Open on the metric where the two sit furthest apart, with the other three a tab away.
Final-text delay after the speaker stops. Lower is better.
| # | Model | Final text | turns | |
|---|---|---|---|---|
| 1 | Soniox STT-RT v5 | 38ms | 200 | |
| 2 | Inworld STT-1 | 41ms | 206 | |
| 3 | AssemblyAI Universal 3.6 Pro | 91ms | 206 | |
| 4 | Deepgram Nova-3 | 103ms | 202 | |
| 5 | Deepgram Flux English | 108ms | 199 | |
| 6 | Deepgram Flux Multilingual | 114ms | 175 | |
| 7 | Cartesia Ink 2 | 123ms | 198 | |
| 8 | Speechmatics Linden | 147ms | 194 | |
| 9 | AssemblyAI Universal 3.5 Pro | 180ms | 205 | |
| 10 | Smallest Pulse | 201ms | 206 | |
| 11 | Gradium | 212ms | 198 | |
| 12 | Reson8 | 235ms | 201 | |
| 13 | Google Chirp 3 | 475ms | 206 | |
| 14 | GPT Realtime Whisper | 543ms | 206 | |
| 15 | Google Chirp 2 | 568ms | 205 | |
| 16 | GPT-4o Mini Transcribe | 630ms | 206 | |
| 17 | GPT-4o Transcribe | 652ms | 206 |
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 |
|---|---|---|---|---|
| Reson8 | 1,000 | 8 | 201 | 0 |
| Soniox STT-RT v5 | 1,000 | 8 | 200 | 6 |
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 Reson8 or Soniox STT-RT v5 more accurate?
On the 1,000 public Pipecat clips, Reson8 scores 2.10% and Soniox STT-RT v5 2.54%, so Reson8 makes fewer errors by 0.45 points. On the eight licensed Ocular recordings, Reson8 scores 2.93% and Soniox STT-RT v5 3.92%, so Reson8 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, Reson8 or Soniox STT-RT v5?
Soniox STT-RT v5 returns first text 1.21s sooner, at 1.20s against 2.40s at the median. Soniox STT-RT v5 has the final transcript 197ms sooner, 38ms after the speaker stops against 235ms. Both are measured on the same 206 streamed turns.
How were Reson8 and Soniox STT-RT v5 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. Reson8 returned usable text for 1,000 of the public clips and Soniox STT-RT v5 for 1,000. Latency uses each provider's own supported finalization contract.