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)→
More from Models
- Meta expands Muse Spark 1.2 globally with 1M context at $0.10 per million tokens — qinzytech · 2026-08-26
- Users Report Degraded Readability in Fable and Opus Outputs — nrehiew_ · 2026-08-26
- Study finds LLMs susceptible to 'Prior-hacking', derailing reasoning — RexDouglass · 2026-08-26
- Dev calls for automatic model routing in Gemini API for cost and rate-limit fallback — EvanOtero · 2026-08-26
- MiniMax M3 is free on GMI Cloud and OpenRouter until September 6 — Porn197617_ · 2026-08-26
- Ask HN: What is one simple thing LLMs are insanely bad at? — davidest · 2026-08-26