Skip to content
The Humanness Index™
Built by VapiGitHub

The Humanness Index™

The open benchmark for how human voice AI sounds, so you can pick the model that passes. Built by Vapi.

MethodologyGitHubContactvapi.ai

Code is Apache-2.0. Standings data is CC BY 4.0. Audio clips and source voices are licensed recordings, all rights reserved. Provider logomarks belong to their respective owners and are used nominatively. “The Humanness Index™” name and logo are Vapi trademarks; see TRADEMARKS.md.

  1. Humanness Index™
  2. Cartesia

Humanness Index™ · Provider

Cartesia

Cartesia

cartesia.ai

Cartesia was founded by the researchers who created state space models, the S4 and Mamba architectures from their academic work.

Best ranked model
#12 Sonic 3.5
Humanness
70

Standings as of Jul 28, 2026, 00:49 UTC

Cartesia
Models on the Index
4
Languages
42
Price / 1M chars
$50
Visit Cartesia

Cartesia models on the Humanness Index™

RankModelHumannessLatencyLanguagesPrice / 1M chars
#20Sonic0116 ms15$50
#15Sonic 267159 ms15$50
#16Sonic 365166 ms42$50
#12Sonic 3.570128 ms42$50

Compare against the full Humanness Index™ rankings

About Cartesia

Cartesia was founded by the researchers who created state space models, the S4 and Mamba architectures from their academic work. Every Sonic generation is a state space model rather than a Transformer, which is the architectural basis of the latency claims the family is known for.

Sources: cartesia.ai

Platform and compliance

Four Sonic generations sit on the Humanness Index™, from the May 2024 debut model to the current Sonic 3.5 flagship. Since Sonic 3 the platform has carried SOC 2 Type II, HIPAA, and PCI Level 1 compliance, aimed at regulated phone work.

Sources: docs.cartesia.ai

Cartesia stats

Languages
421
Price / 1M chars
$502
  1. docs.cartesia.ai (checked 2026-06-10) Sonic 3 and 3.5; earlier Sonic and Sonic 2 shipped 15, encoded per model.
  2. cartesia.ai/pricing (checked 2026-06-10) 1 credit per character (docs.cartesia.ai/pricing); entry self-serve Pro plan is $5/mo for 100K credits, a $50 per 1M effective rate; larger plans drop to $37-39 per 1M. Same credit rate for every Sonic.

Other providers on the Index

ElevenLabsElevenLabsBest ranked model #1 · Eleven v3xAIxAIBest ranked model #2 · Grok TTSMiniMaxMiniMaxBest ranked model #3 · Speech 2.8GradiumGradiumBest ranked model #19 · Gradium TTSCanopy LabsCanopy LabsBest ranked model #4 · OrpheusInworldInworldBest ranked model #8 · TTS-1.5-maxSmallest.aiSmallest.aiBest ranked model #17 · Lightning v3.1NeuphonicNeuphonicBest ranked model #18 · neu_hqSpeechifySpeechifyBest ranked model #7 · Simba 3.2HumanHumanBaseline reference · Humanness 100

Back to the Humanness Index™

Find the most human-sounding voice for your agent.

Compare the models in blind tests, read the methodology, or get in touch.

Read the methodologyStar on GitHub

Build a TTS model? Add yours to the Index.