Cartesia vs Deepgram

Cartesia holds a tighter latency spread than either Deepgram model.

Callers hear the slow turns, not the average.

2X Solutions logo
arini logo
toby logo

Latency consistency

Sonic 3.5's slowest calls stay close to its fastest

  • An average hides the calls that break a conversation. The spread is what a caller actually hears.
  • Sonic 3.5's slowest measured call stays under half a second. Both Deepgram models run past that.

Latency Variation: Distribution of TTFA values

Lower is better

CovalAugust 2026
0ms100ms200ms300ms400ms500ms600ms700ms800ms
Sonic 3.5
Cartesia
Aura-2
Deepgram
Flux
Deepgram

Tail latency

Cartesia stays ahead where it counts most

  • P95 is the turn that one caller in twenty gets, so it sets how often a conversation stalls.
  • Sonic 3.5 answers faster than both Deepgram models at that percentile, and it is the only one of the three whose spread stays narrow enough to be predictable.

Latency at P95

Lower is better

CovalAugust 2026
370ms
547ms
590ms
Sonic 3.5
Cartesia
Aura-2
Deepgram
Flux
Deepgram

Accuracy

Sonic 3.6 makes fewer word errors than both Deepgram models

  • Coval transcribes every clip each model generates and compares it with the script, so a lower rate means more of the script is spoken as written.
  • Sonic 3.6 misreads fewer words than Flux and Aura-2, so names, numbers, and codes come through as written.

Word error rate

Lower is better

CovalSeptember 2026
1.99%
2.2%
2.78%
Sonic 3.6
Cartesia
Flux
Deepgram
Aura-2
Deepgram

Reasons why companies choose Cartesia over Deepgram

CartesiaDeepgram
  1. Consistency

    Coval
    Cartesia
    63ms interquartile range
    Deepgram
    211ms interquartile rangeAura-2300ms interquartile rangeFlux

    August 2026

  2. Accuracy

    Coval
    Cartesia
    1.99% word error rateSonic 3.6
    Deepgram
    2.20% word error rateFlux2.78% word error rateAura-2

    September 2026

  3. Languages

    Cartesia
    44 languages from one model, with region-calibrated accents
    Deepgram
    7 languages
  4. Voice range

    Cartesia
    Full voice library, instant clone from 10 seconds, professional clone from 30 minutes
    Deepgram
    88 preset voices
  5. Deployment

    Cartesia
    VPC, on-prem, on-device, or air-gapped, backed by a 99.9% uptime SLA
    Deepgram
    Self-hosting requires an Enterprise plan

Frequently asked questions

Get started today

Talk to an expert.

Connect with a member of our team and learn how Cartesia can help you build world-class voice experiences.

Contact Sales

Start building.

Access our models via API and bring a voice agent into production in minutes.

Try Cartesia