Humanness Index™ · TTS model
by ElevenLabs
Turbo v2.5 arrived in July 2024 and extended ElevenLabs' low latency tier from English to 32 languages, making Hindi, French, Spanish, Mandarin and more roughly three times faster than before, with English itself about 25 percent faster.
Standings as of Jun 13, 2026, 00:15 UTC
A real arena clip: a cloned source voice reading a customer support prompt at phone quality.
Turbo v2.5 arrived in July 2024 and extended ElevenLabs' low latency tier from English to 32 languages, making Hindi, French, Spanish, Mandarin and more roughly three times faster than before, with English itself about 25 percent faster. ElevenLabs has since positioned Flash v2.5 as its successor. On the Humanness Index™, Turbo v2.5 is currently the strongest ElevenLabs model in blind listening tests.
Sources: elevenlabs.io
Turbo v2.5 brought 32 languages to the low latency tier when it launched in July 2024. In our 50 trial streaming benchmark it returned first audio in a median of 265 ms.
Sources: elevenlabs.io
Standings as of Jun 13, 2026, 00:15 UTC
| Rank | Provider | Model | Humanness | Latency |
|---|---|---|---|---|
| #4 | Canopy Labs | Orpheus | 78 | — |
| #5 | ElevenLabs | Eleven v3 | 76 | 758 ms |
| #6 | ElevenLabs | Turbo v2.5 | 75 | 265 ms |
| #7 | ElevenLabs | Flash v2.5 | 72 | 197 ms |
| #8 | MiniMax | Speech 2.5 | 71 | 325 ms |
The benchmark is open source. Suggest a model, read the methodology, or ask us to put your voice in the arena.
