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. Canopy Labs

Humanness Index™ · Provider

Canopy Labs

Canopy Labs

canopylabs.ai

Canopy Labs is the team behind Orpheus, the open source speech LLM family released in March 2025 under the Apache 2.0 license.

Best ranked model
#4 Orpheus
Humanness
78

Standings as of Jun 13, 2026, 00:15 UTC

Canopy Labs
Models on the Index
1
Languages
English
Price / 1M chars
Open source
Visit Canopy Labs

Canopy Labs models on the Humanness Index™

RankModelHumannessLatencyLanguagesPrice / 1M chars
#4Orpheus78—EnglishOpen source

Compare against the full Humanness Index™ rankings

About Canopy Labs

Canopy Labs is the team behind Orpheus, the open source speech LLM family released in March 2025 under the Apache 2.0 license. The company has promised smaller 1B, 400M, and 150M variants alongside the flagship 3B model, and it partners with managed inference providers such as Baseten for production hosting.

Sources: canopylabs.ai, baseten.co

Open weights on the Index

Orpheus is the open weights entry on the Humanness Index™, and it showed that an open model can compete with closed source rivals on prosody and empathy. Teams can self host it or run it through managed providers.

Sources: github.com

Canopy Labs stats

Languages
English1
Price / 1M chars
Open source2
  1. github.com/canopyai/Orpheus-TTS (checked 2026-06-10) Flagship trained on English; a multilingual research preview followed in April 2025.
  2. github.com/canopyai/Orpheus-TTS (checked 2026-06-10) Apache 2.0 code; weights under the Llama 3.2 Community License. No commercial per-character price.

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 #19 · Gradium TTSInworldInworldBest ranked model #9 · TTS-2Smallest.aiSmallest.aiBest ranked model #11 · Lightning v3.1NeuphonicNeuphonicBest ranked model #13 · neu_hq

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