Skip to content

Comparison · read on October 27, 2026

Gradium TTS vs Cartesia Sonic 3.6

Two text-to-speech (TTS) models side by side, from four public benchmarks. Speed comes first, then listener rating and price; the three are never added into a score.

MeasureGradium TTSCartesia Sonic 3.6
ProviderGradiumCartesia
Speed tierHeadroomVisible delay
P95 time to first audio104.3 ms374.4 ms
Median time to first audio53.7 ms285.8 ms
Listener Elo1,1741,292
Price per 1M characters$36 to $57.8$39.2 to $50
AccessProprietaryProprietary
Rank in the full ranking218
Rank by use caseCustomer service 1, Voice agents 2, Assistants 1, Entertainment 1, Knowledge sharing 1Customer service 12, Assistants 12, Entertainment 12, Knowledge sharing 12

Which should you choose?

Where a model is not timed or not rated, nothing is estimated. See each model page for its sources: Gradium TTS and Cartesia Sonic 3.6.

Frequently asked questions

Which is faster, Gradium TTS or Cartesia Sonic 3.6?
Speed: Gradium TTS comes out ahead (104.3 ms against 374.4 ms at P95).
Which is rated higher by listeners, Gradium TTS or Cartesia Sonic 3.6?
Listener rating: Cartesia Sonic 3.6 comes out ahead (Elo 1,174 against 1,292; scores within each other's 95% intervals are a tie).
Which is cheaper, Gradium TTS or Cartesia Sonic 3.6?
Price: Gradium TTS comes out ahead ($36 to $57.8 against $39.2 to $50 per million characters, lowest list price).
Why is this model always on the left?
Gradium TTS is the reference model of this site's comparison pages: it is set against every other listed model. The editor chose it; it is not chosen by rank.