OpenAI vs Deepgram: Speech-to-Textlatency & accuracy
Measured head-to-head, not marketing: the verdict is split — Deepgram is faster (98 ms median TTFS vs 632 ms), while OpenAI is more accurate (2.6% WER vs 4.5%). Independent data, refreshed daily, on identical inputs. Voice quality and price are not measured.
OpenAI or Deepgram — which is better?
Each provider's best model on each measured axis, last 7d. Lower is better on both:
| Axis | OpenAI (best model) | Deepgram (best model) | Measured winner |
|---|---|---|---|
| Speed — median TTFS | gpt-4o-mini-transcribe · 632 ms | nova-3 · 98 ms | Deepgram |
| Accuracy — avg WER | gpt-4o-mini-transcribe · 2.6% | nova-3 · 4.5% | OpenAI |
Not measured here: price — treat those as vendor claims until measured. Full leaderboard context: the independent speech-to-text benchmark →
Every OpenAI 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 |
|---|---|---|---|---|---|
| nova-3 | Deepgram | 98 ms | 154 ms | 4.5% | 3,327 |
| nova-2 | Deepgram | 98 ms | 175 ms | 5.2% | 3,330 |
| gpt-4o-mini-transcribe | OpenAI | 632 ms | 1,236 ms | 2.6% | 3,347 |
| gpt-realtime-whisper | OpenAI | 666 ms | 821 ms | 3.3% | 3,347 |
| gpt-4o-transcribe | OpenAI | 767 ms | 1,158 ms | 3.1% | 3,353 |
Independent data, by Coval
Numbers are from the voice benchmark by Coval, a voice-AI evaluation platform that does not sell STT models — it measures every provider as a neutral third party on a pinned dataset under production-realistic conditions. Openbenchmarks mirrors the results daily with attribution; methodology and runner are open-source and reproducible.
OpenAI vs Deepgram — common questions
Is OpenAI faster than Deepgram for speech-to-text?
On the current 7d window, OpenAI's fastest model (gpt-4o-mini-transcribe) has a median TTFS of 632 ms, vs 98 ms for Deepgram's fastest (nova-3) — so Deepgram is faster on measured median latency. Distributions matter too: p95 is 1,236 ms for OpenAI vs 154 ms for Deepgram.
Which is more accurate, OpenAI or Deepgram?
By Word Error Rate: OpenAI's best model (gpt-4o-mini-transcribe) averages 2.6%, vs 4.5% for Deepgram's best (nova-3) — OpenAI leads on measured accuracy. Lower is better; WER is measured on identical inputs under production-realistic conditions.
Which should I pick — OpenAI or Deepgram?
The measured verdict is split: Deepgram is faster (median TTFS), OpenAI is more accurate (WER). Pick by your constraint — real-time voice agents care about latency; fidelity-critical workloads care about WER. Note price is not measured here.
Where does this data come from?
The independent voice benchmark by Coval, a voice-AI evaluation platform that does not sell STT models. Every model runs the same pinned dataset under production-realistic conditions, re-run roughly every 30 minutes; Openbenchmarks mirrors the results daily with attribution. Methodology and runner are open-source (Apache-2.0).