Cartesia vs Deepgram: Text-to-Speechlatency & accuracy
Measured head-to-head, not marketing: Cartesia currently leads both measured axes — median TTFA and Word Error Rate. Independent data, refreshed daily, on identical inputs. Voice quality and price are not measured.
Cartesia or Deepgram — which is better?
Each provider's best model on each measured axis, last 7d. Lower is better on both:
| Axis | Cartesia (best model) | Deepgram (best model) | Measured winner |
|---|---|---|---|
| Speed — median TTFA | sonic-3.5 · 277 ms | aura-2-thalia-en · 331 ms | Cartesia |
| Accuracy — avg WER | sonic-3.5 · 6.0% | aura-2-thalia-en · 8.0% | Cartesia |
Not measured here: voice quality / naturalness and price — treat those as vendor claims until measured. Full leaderboard context: the independent text-to-speech benchmark →
Every Cartesia and Deepgram model, measured
All benchmarked models from both providers on the same pinned dataset, ranked fastest-first (median TTFA), last 7d:
| Model | Provider | TTFA median | TTFA p95 | WER | Samples |
|---|---|---|---|---|---|
| sonic-3.5 | Cartesia | 277 ms | 355 ms | 6.0% | 3,358 |
| aura-2-thalia-en | Deepgram | 331 ms | 542 ms | 8.0% | 3,353 |
| sonic-3 | Cartesia | 461 ms | 826 ms | 6.7% | 3,356 |
Independent data, by Coval
Numbers are from the voice benchmark by Coval, a voice-AI evaluation platform that does not sell TTS 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.
Cartesia vs Deepgram — common questions
Is Cartesia faster than Deepgram for text-to-speech?
On the current 7d window, Cartesia's fastest model (sonic-3.5) has a median TTFA of 277 ms, vs 331 ms for Deepgram's fastest (aura-2-thalia-en) — so Cartesia is faster on measured median latency. Distributions matter too: p95 is 355 ms for Cartesia vs 542 ms for Deepgram.
Which is more accurate, Cartesia or Deepgram?
By Word Error Rate: Cartesia's best model (sonic-3.5) averages 6.0%, vs 8.0% for Deepgram's best (aura-2-thalia-en) — Cartesia leads on measured accuracy. Lower is better; WER is measured on identical inputs under production-realistic conditions.
Which should I pick — Cartesia or Deepgram?
Cartesia currently leads both measured axes (median TTFA and WER). Full per-model distributions are in the table below; voice quality / naturalness and price are not measured here.
Where does this data come from?
The independent voice benchmark by Coval, a voice-AI evaluation platform that does not sell TTS 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).