Neuphonic models on the Humanness Index™
| Rank | Model | Humanness | Latency | Languages | Price / 1M chars |
|---|
| #13 | neu_hq | 63 | 276 ms | 9 | — |
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
- Price / 1M chars
- —No published pricing to cite yet.
- docs.neuphonic.com/build-group/languages (checked 2026-06-12) English, Chinese, French, German, Japanese, Korean, Spanish, Portuguese, and Urdu.
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.