Deepgram Flux Multilingual vs Soniox STT-RT v5
Soniox STT-RT v5 is ahead on the Pipecat Dataset and final-text delay, and Deepgram Flux Multilingual on time to first text. The Ocular Dataset is too close to call.
Last updated Methodology by Dileep Chagam
Accuracy vs speed
Each dot is one model. Bottom-left is best: fewer errors and a faster final transcript.
Which to pick
Pick Deepgram Flux Multilingual for showing words while the caller is still talking (402ms sooner). Pick Soniox STT-RT v5 for accuracy on clean, scripted audio (2.41 points lower) and quick turn-taking once the caller stops (76ms sooner). For accuracy on real phone conversations, the gap is inside the margin of error, so neither is ahead.
The four metrics, side by side
- Deepgram Flux Multilingual
- 4.96%16th
- Soniox STT-RT v5
- 2.54%8th
Soniox STT-RT v5, 2.41 points lower
- Deepgram Flux Multilingual
- 4.53%15th
- Soniox STT-RT v5
- 3.92%6th
Too close to call: inside the margin of error
- Deepgram Flux Multilingual
- 793ms4th
- Soniox STT-RT v5
- 1.20s9th
Deepgram Flux Multilingual, 402ms sooner
- Deepgram Flux Multilingual
- 114ms6th
- Soniox STT-RT v5
- 38ms1st
Soniox STT-RT v5, 76ms sooner
Lower is better on every metric. The small figure is each model's place in the whole field. What each metric measures.
- WER · Word error rate
- Share of words the model got wrong: replaced, missing or added. Lower is better.
- Pipecat Dataset
- 1,000 short public clips from Pipecat's STT benchmark dataset.
- Ocular Dataset
- 8 recordings from 4 real phone conversations, licensed from Ocular.
- TTFT · Time to first text
- How long after the audio starts streaming until the first words appear.
- TTFS · Final-text delay
- How long after the caller stops until the full transcript arrives. A voice agent waits for this before it replies.
First text and final text, at three percentiles
Deepgram Flux Multilingual shows first text after 3.41s and final text after 141ms, and Soniox STT-RT v5 shows first text after 1.71s and final text after 79ms, on a bad turn (P95) across the same streamed turns.
| Measure | Model | P50 | P90 | P95 |
|---|---|---|---|---|
| Time to first text | Deepgram Flux Multilingual | 793ms | 2.00s | 3.41s |
| Soniox STT-RT v5 | 1.20s | 1.67s | 1.71s | |
| Final-text delay | Deepgram Flux Multilingual | 114ms | 135ms | 141ms |
| Soniox STT-RT v5 | 38ms | 72ms | 79ms |
- P50 / P90 / P95 · Typical, slow and slowest turns
- Half of turns are faster than P50. Only 1 in 10 is slower than P90, and 1 in 20 slower than P95.
How each ranks among all 17 models
Place among the 17 models on each metric. Lower is better on all four.
| Metric | Flux Multilingual | STT-RT v5 |
|---|---|---|
| Pipecat Dataset WER | 4.96%16th of 17 | 2.54%8th of 17 |
| Ocular Dataset WER | 4.53%15th of 17 | 3.92%6th of 17 |
| Time to first text | 793ms4th of 15 | 1.20s9th of 15 |
| Final-text delay | 114ms6th of 17 | 38ms1st of 17 |
How much audio each model was tested on
| Model | Pipecat clips | Ocular recordings | Turns timed | Failed |
|---|---|---|---|---|
| Deepgram Flux Multilingual | 999 | 8 | 175 | 31 |
| Soniox STT-RT v5 | 1,000 | 8 | 200 | 6 |
Only clips with usable text count, so the two totals can differ. How WER is scored.
Related comparisons
- Deepgram Flux Multilingual vs Deepgram Flux English
- Deepgram Flux Multilingual vs GPT-4o Transcribe
- Deepgram Flux Multilingual vs Smallest Pulse
- Deepgram Flux Multilingual vs Deepgram Nova-3
- Deepgram Flux Multilingual vs Gradium
- Deepgram Flux Multilingual vs GPT-4o Mini Transcribe
- Deepgram Flux Multilingual vs Inworld STT-1
- Deepgram Flux Multilingual vs Speechmatics Linden
- Deepgram Flux Multilingual vs Cartesia Ink 2
- Deepgram Flux Multilingual vs GPT Realtime Whisper
- Deepgram Flux Multilingual vs Reson8
- Deepgram Flux Multilingual vs Google Chirp 3
- Deepgram Flux Multilingual vs AssemblyAI Universal 3.6 Pro
- Soniox STT-RT v5 vs Speechmatics Linden
- Soniox STT-RT v5 vs Cartesia Ink 2
- Soniox STT-RT v5 vs Inworld STT-1
- Soniox STT-RT v5 vs GPT Realtime Whisper
- Soniox STT-RT v5 vs Reson8
- Soniox STT-RT v5 vs Google Chirp 3
- Soniox STT-RT v5 vs AssemblyAI Universal 3.6 Pro
- Soniox STT-RT v5 vs GPT-4o Mini Transcribe
- Soniox STT-RT v5 vs Deepgram Nova-3
- Soniox STT-RT v5 vs Smallest Pulse
- Soniox STT-RT v5 vs GPT-4o Transcribe
- Soniox STT-RT v5 vs Deepgram Flux English
- Soniox STT-RT v5 vs Gradium
Frequently asked questions
Which is more accurate, Deepgram Flux Multilingual or Soniox STT-RT v5?
Soniox STT-RT v5 is more accurate on the public clips. On the 1,000 public Pipecat clips, Deepgram Flux Multilingual scores 4.96% and Soniox STT-RT v5 2.54%, so Soniox STT-RT v5 makes fewer errors by 2.41 points. On the eight licensed Ocular recordings, Deepgram Flux Multilingual scores 4.53% and Soniox STT-RT v5 3.92%, with likely ranges of 3.29 to 5.69% and 2.60 to 4.86%. The ranges overlap, so the difference is too close to call. Word error rate counts incorrect, missing, and extra words, so lower is better.
Is Deepgram Flux Multilingual faster than Soniox STT-RT v5?
No. Soniox STT-RT v5 finishes the transcript 76ms sooner. Deepgram Flux Multilingual has the final transcript 114ms after the speaker stops and Soniox STT-RT v5 38ms, at the median. Both are measured on the same 206 streamed turns.
Is Deepgram Flux Multilingual or Soniox STT-RT v5 better for voice agents?
Soniox STT-RT v5 finishes the transcript 76ms sooner, and the two are too close to call on real conversations. A voice agent cannot reply until the final transcript arrives, and the Ocular recordings are real conversations.
Do Deepgram Flux Multilingual and Soniox STT-RT v5 stream text while the speaker is talking?
Yes, both return partial text before the speaker stops. Deepgram Flux Multilingual shows first text after 793ms and Soniox STT-RT v5 after 1.20s, at the median, so Deepgram Flux Multilingual is 402ms sooner.