Voxtral 3 TTS Tops Speed Charts at 112 chars/sec, Undercuts Eleven v4 Turbo by 3x on Price
ArtificialAnlys · x · 2026-10-21
Artificial Analysis rounded up its speech leaderboards with fresh data on Voxtral 3 TTS:
- Speed: Voxtral 3 TTS generates 112.3 characters/sec, well ahead of Eleven v4 Turbo (78.1), Simba 3.2 (77.8), Gemini 3.8 Flash TTS (55.3), and Breeze TTS 2 (43.4)
- Pricing: $13/1M characters — cheaper than Gemini 3.8 Flash TTS ($16.5), Breeze TTS 2 ($34), and Eleven v4 Turbo ($40), though above Simba 3.2 ($6.6)
- Quality: In the Provider Voice Arena, Voxtral 3 TTS scores 1218 Elo, trailing Eleven v4 Turbo (1330), Eleven v4 (1328), Qwen-Audio-3.1-TTS-Plus (1298), and Sonic 3.6 (1290)
Other top entries include Gemini 3.8 Flash TTS (1279, $16.5/1M), Fish Audio Drama 3 Preview, and StepAudio 2.5. Users can vote in the Speech Arena or audition clips in the Speech Explorer.
More from Models
- Ex-Google insider: compute bottlenecks go beyond power; open models replacing frontier APIs — xiaosun86 · 2026-10-21
- Fable 5.5 leak: litellm code shows Anthropic model in staging, launch tipped for Oct 27 — imjustnewatai · 2026-10-21
- Open models below 4-bit struggle at self-iterating 3D asset generation, HF dev finds — mervenoyann · 2026-10-21
- Researcher Finds Two Windows 0-Days, First in 76 Minutes with a Frontier Model — moyix · 2026-10-21
- Dev finds Gemini Argon's debug-log analysis beats Fable 5.1 — ShikharMurty · 2026-10-21
- ChatGPT Gets Stuck Screaming "AAHH" in an Infinite Loop After a Simple Prompt — AutomaticScene · 2026-10-21