Inworld STT-1 vs Soniox STT-RT v5
Inworld STT-1 is ahead on time to first text, and Soniox STT-RT v5 on final-text delay. The Pipecat Dataset and The Ocular Dataset are 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 Inworld STT-1 for showing words while the caller is still talking (132ms sooner). Pick Soniox STT-RT v5 for quick turn-taking once the caller stops (3ms sooner). For accuracy on clean, scripted audio and accuracy on real phone conversations, the gap is inside the margin of error, so neither is ahead.
The four metrics, side by side
- Inworld STT-1
- 2.72%10th
- Soniox STT-RT v5
- 2.54%8th
Too close to call: inside the margin of error
- Inworld STT-1
- 10.60%16th
- Soniox STT-RT v5
- 3.92%6th
Too close to call: inside the margin of error
- Inworld STT-1
- 1.06s6th
- Soniox STT-RT v5
- 1.20s9th
Inworld STT-1, 132ms sooner
- Inworld STT-1
- 41ms2nd
- Soniox STT-RT v5
- 38ms1st
Soniox STT-RT v5, 3ms 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
Inworld STT-1 shows first text after 1.07s and final text after 65ms, 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 | Inworld STT-1 | 1.06s | 1.07s | 1.07s |
| Soniox STT-RT v5 | 1.20s | 1.67s | 1.71s | |
| Final-text delay | Inworld STT-1 | 41ms | 60ms | 65ms |
| 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 | STT-1 | STT-RT v5 |
|---|---|---|
| Pipecat Dataset WER | 2.72%10th of 17 | 2.54%8th of 17 |
| Ocular Dataset WER | 10.60%16th of 17 | 3.92%6th of 17 |
| Time to first text | 1.06s6th of 15 | 1.20s9th of 15 |
| Final-text delay | 41ms2nd of 17 | 38ms1st of 17 |
How much audio each model was tested on
| Model | Pipecat clips | Ocular recordings | Turns timed | Failed |
|---|---|---|---|---|
| Inworld STT-1 | 1,000 | 8 | 206 | 0 |
| 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
- Inworld STT-1 vs Speechmatics Linden
- Inworld STT-1 vs Cartesia Ink 2
- Inworld STT-1 vs GPT Realtime Whisper
- Inworld STT-1 vs Reson8
- Inworld STT-1 vs GPT-4o Mini Transcribe
- Inworld STT-1 vs Google Chirp 3
- Inworld STT-1 vs Deepgram Nova-3
- Inworld STT-1 vs Smallest Pulse
- Inworld STT-1 vs AssemblyAI Universal 3.6 Pro
- Inworld STT-1 vs GPT-4o Transcribe
- Inworld STT-1 vs Deepgram Flux English
- Inworld STT-1 vs Deepgram Flux Multilingual
- Inworld STT-1 vs Gradium
- Soniox STT-RT v5 vs Speechmatics Linden
- Soniox STT-RT v5 vs Cartesia Ink 2
- 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 Deepgram Flux Multilingual
- Soniox STT-RT v5 vs Gradium
Frequently asked questions
Which is more accurate, Inworld STT-1 or Soniox STT-RT v5?
Inworld STT-1 and Soniox STT-RT v5 are too close to call on accuracy. On the 1,000 public Pipecat clips, Inworld STT-1 scores 2.72% and Soniox STT-RT v5 2.54%, with likely ranges of 1.67 to 4.68% and 2.27 to 2.83%. The ranges overlap, so the difference is too close to call. On the eight licensed Ocular recordings, Inworld STT-1 scores 10.60% and Soniox STT-RT v5 3.92%, with likely ranges of 3.85 to 22.76% 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 Inworld STT-1 faster than Soniox STT-RT v5?
No. Soniox STT-RT v5 finishes the transcript 3ms sooner. Inworld STT-1 has the final transcript 41ms after the speaker stops and Soniox STT-RT v5 38ms, at the median. Both are measured on the same 206 streamed turns.
Is Inworld STT-1 or Soniox STT-RT v5 better for voice agents?
Soniox STT-RT v5 finishes the transcript 3ms 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 Inworld STT-1 and Soniox STT-RT v5 stream text while the speaker is talking?
Yes, both return partial text before the speaker stops. Inworld STT-1 shows first text after 1.06s and Soniox STT-RT v5 after 1.20s, at the median, so Inworld STT-1 is 132ms sooner.