Bland AI Launches Speech v3, Topping Blind Audio Realism Bench

mhdfaran · x · 2026-08-06

Bland AI has released Speech v3, a new text-to-speech model claiming the #1 spot on the Audio Realism Bench with an Elo rating of 1384, reportedly beating out real human speech recordings.

In this blind listening benchmark by intelligence.ai, vetted native listeners compare two unlabelled models reading the same script. Bland Speech v3 outperformed major TTS competitors including ElevenLabs, GPT-4o Mini, and Gemini. The company has provided several demo audios and opened the model for free user testing.

Related event: Bland AI Launches Speech v3, Topping Audio Blind Tests(4 posts)→

Original post →

More from Models

Models channel →