---
title: "Soniox vs Deepgram: live STT accuracy and latency, independent benchmark | Openbenchmarks"
description: "Soniox vs Deepgram speech-to-text, compared on a live rolling 7-day Word Error Rate and Time to Final Segment (TTFS). Independent benchmark data on identical audio. Not vendor claims."
url: https://openbenchmarks.com/speech-to-text-benchmark-by-coval/soniox-vs-deepgram
---

[](https://openbenchmarks.com/) 

[← stt benchmark](https://openbenchmarks.com/speech-to-text-benchmark-by-coval) 

[benchmarks](https://openbenchmarks.com/) / [stt by coval](https://openbenchmarks.com/speech-to-text-benchmark-by-coval) / soniox vs deepgram 

speech-to-text head-to-head · data by Coval 

# Soniox vs Deepgram: Speech-to-Textlatency & accuracy

Measured head-to-head, not marketing: **Soniox** currently leads both measured axes: median TTFS and Word Error Rate. Independent data, refreshed daily, on identical inputs. Price and whether emails, phones, paths, and IDs survive verbatim are not measured.

\[00\] verdict

## Soniox or Deepgram: which is better?

Each provider's best model on each measured axis, last 7d. Lower is better on both:

| Axis | Soniox (best model) | Deepgram (best model) | Measured winner |
| --- | --- | --- | --- |
| **Speed**: median TTFS | stt-rt-v5 · **36 ms** | nova-3 · **90 ms** | **Soniox** |
| **Accuracy**: avg WER | stt-rt-v5 · **4.8%** | nova-3 · **5.1%** | **Soniox** |

Not measured here: **price, hallucination on silence, endpointing, timestamps, diarization, long-form drift, rate limits, and whether emails, phones, paths, and IDs survive verbatim**. Treat those as vendor claims until measured. Full leaderboard context: [the independent speech-to-text benchmark →](https://openbenchmarks.com/speech-to-text-benchmark-by-coval) 

\[01\] every model

## Every Soniox and Deepgram model, measured

All benchmarked models from both providers on the same pinned dataset, ranked fastest-first (median TTFS), last 7d:

| Model | Provider | TTFS median | TTFS p95 | WER | Samples |
| --- | --- | --- | --- | --- | --- |
| **stt-rt-v5** | Soniox | **36 ms** | 65 ms | 4.8% | 6,384 |
| **nova-3** | Deepgram | **90 ms** | 135 ms | 5.1% | 6,381 |
| **nova-2** | Deepgram | **91 ms** | 144 ms | 6.6% | 6,368 |
| **flux-general-en** | Deepgram | **99 ms** | 164 ms | 5.7% | 6,384 |
| **flux-general-multi** | Deepgram | **101 ms** | 164 ms | 7.4% | 6,384 |

\[02\] source

## Data by Coval

Coval sells voice-agent evaluation infrastructure. Numbers are a rolling 7d aggregate on a pinned dataset under production-realistic conditions. Openbenchmarks mirrors the results with attribution; methodology and runner are open-source.

synced from Coval 2026-10-11 11:51 UTC · [full STT benchmark →](https://openbenchmarks.com/speech-to-text-benchmark-by-coval) · [methodology →](https://github.com/coval-ai/benchmarks) 

\[03\] faq

## Soniox vs Deepgram: common questions

### Is Soniox faster than Deepgram for speech-to-text?

On the current 7d window, Soniox's fastest model (stt-rt-v5) has a median TTFS of 36 ms, vs 90 ms for Deepgram's fastest (nova-3), so Soniox is faster on measured median latency. Distributions matter too: p95 is 65 ms for Soniox vs 135 ms for Deepgram.

### Which is more accurate, Soniox or Deepgram?

By Word Error Rate: Soniox's best model (stt-rt-v5) averages 4.8%, vs 5.1% for Deepgram's best (nova-3). Soniox leads on measured accuracy. Lower is better; WER is measured on identical inputs under production-realistic conditions.

### Which should I pick, Soniox or Deepgram?

Soniox currently leads both measured axes (median TTFS and WER). Full per-model distributions are in the table below; price, hallucination on silence, endpointing, timestamps, diarization, long-form drift, rate limits, and whether emails, phones, paths, and IDs survive verbatim are not measured here.

### Where does this data come from?

Coval sells voice-agent evaluation infrastructure. Every model runs the same pinned dataset under production-realistic conditions. The table is a rolling 7d aggregate, not a single job; Openbenchmarks mirrors it with attribution. Methodology and runner are open-source (Apache-2.0).