Humanness Index™ · Provider
ElevenLabs is the incumbent voice platform, with model families that span ultra low latency conversational agents to maximum expressiveness.
Standings as of Jun 13, 2026, 00:15 UTC
| Rank | Model | Humanness | Latency | Languages | Price / 1M chars |
|---|---|---|---|---|---|
| #14 | Turbo v2 | 63 | 302 ms | English | $50 |
| #6 | Turbo v2.5 | 75 | 265 ms | 32 | $50 |
| #17 | Flash v2 | 57 | 226 ms | English | $50 |
| #7 | Flash v2.5 | 72 | 197 ms | 32 | $50 |
| #5 | Eleven v3 | 76 | 758 ms | 70+ | $100 |
| #16 | Multilingual v2 | 61 | 1006 ms | 29 | $100 |
ElevenLabs is the incumbent voice platform, with model families that span ultra low latency conversational agents to maximum expressiveness. Latency and language coverage vary sharply across those families, so every ElevenLabs model on the Humanness Index™ carries its own figures rather than one provider-wide number.
Sources: elevenlabs.io
Six ElevenLabs models sit on the Index, spanning the Turbo, Flash, Multilingual, and v3 families. ElevenLabs bills in credits: Flash and Turbo models bill one credit per two characters, while Eleven v3 and Multilingual v2 bill one credit per character, which is why those two carry a higher effective rate.
Sources: elevenlabs.io, elevenlabs.io
The benchmark is open source. Suggest a model, read the methodology, or ask us to put your voice in the arena.
