Skip to content
The Humanness Index™
Built by VapiGitHub

The Humanness Index™

The open benchmark for how human voice AI sounds. Built and operated 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. Neuphonic

Humanness Index™ · Provider

Neuphonic

Neuphonic

neuphonic.com

Neuphonic is a London voice AI startup founded in 2024 by Jiameng Gao and Sohaib Ahmad, focused on low latency text to speech APIs and on-device voice.

Best ranked model
#13 neu_hq
Humanness
63

Standings as of Jun 13, 2026, 01:14 UTC

Neuphonic
Models on the Index
1
Languages
9
Price / 1M chars
—
Visit Neuphonic

Neuphonic models on the Humanness Index™

RankModelHumannessLatencyLanguagesPrice / 1M chars
#13neu_hq63276 ms9—

Compare against the full Humanness Index™ rankings

About Neuphonic

Neuphonic is a London voice AI startup founded in 2024 by Jiameng Gao and Sohaib Ahmad, focused on low latency text to speech APIs and on-device voice. It raised a 3M pound pre-seed in October 2024 on the back of a closed beta, and alongside the hosted API it publishes the open source NeuTTS family of on-device speech models with instant cloning.

Sources: thesaasnews.com, github.com

Platform

The hosted API streams over SSE and WebSockets with a per-request language code across nine languages, clones a voice from a short clean sample, and layers a conversational agents product on top. Neuphonic marked version 1.0.0 of the API in August 2025.

Sources: docs.neuphonic.com, docs.neuphonic.com

Neuphonic stats

Languages
91
Price / 1M chars
—No published pricing to cite yet.
  1. docs.neuphonic.com/build-group/languages (checked 2026-06-12) English, Chinese, French, German, Japanese, Korean, Spanish, Portuguese, and Urdu.

Other providers on the Index

ElevenLabsElevenLabsBest ranked model #5 · Eleven v3CartesiaCartesiaBest ranked model #3 · Sonic 3.5xAIxAIBest ranked model #1 · Grok TTSMiniMaxMiniMaxBest ranked model #8 · Speech 2.5GradiumGradiumBest ranked model #20 · Gradium TTSCanopy LabsCanopy LabsBest ranked model #4 · OrpheusInworldInworldBest ranked model #9 · TTS-2Smallest.aiSmallest.aiBest ranked model #14 · Lightning v3.1

Back to the Humanness Index™

How human does your model really sound?

The benchmark is open source. Suggest a model, read the methodology, or ask us to put your voice in the arena.

Add your modelStar on GitHub