Cartesia
How Sonic 3.5 compares with the other 99 text to speech models.
Strong choice. Ranked #21 of 100, 142 Elo points behind #1 and ahead of 80% of models.
Close race with 11 models. Its score range overlaps with Realtime TTS-2 Flash, v3 Conversational, StepAudio 2.5 TTS and 8 more, so you may not notice a difference.
Usually wins. Against a typical model it gets picked in about 65% of blind votes.
Rank
#21
of 100 models
Elo rating
1,194
142 behind #1
typical 1,086
± range
±11
how certain the score is
Votes
–
blind comparisons
This model next to its closest competitors. Click another bar to open that model.
How often people would pick this model over another in a blind vote, based on the Elo scores.
People see two results for the same prompt without knowing which model made them, and vote for the better one. Gaps under about 20 Elo points are hard to notice in practice.
Benchmark data from Artificial Analysis, an independent benchmarking company. Rankings refresh every few hours.
kitio.ai