Cartesia Sonic 3.6 tops Artificial Analysis speech Elo leaderboard at 1123
ArtificialAnlys · x · 2026-08-18
Artificial Analysis's controlled voice leaderboard (same 8 cloned voices, 4 US / 4 UK) has a new leader: Cartesia Sonic 3.6 at Elo 1123, generating 136.1 chars/sec at $49 per 1M characters, ahead of its predecessor Sonic 3.5 at 1102.
ElevenLabs Eleven v3 (1059, $100/1M chars) takes third, followed by StepFun StepAudio 2.5 TTS, Inworld Realtime TTS 1.5 Max and its Research Preview. MiniMax Speech 2.8 HD and Turbo sit at 1027/1026. Open-weight entries include Mistral Voxtral TTS (1011) and Fish Audio S2 Pro (1004); the cheapest top model is SpeechifyAI Simba 3.0 at $12.5/1M chars (1017).
Related event: Cartesia Sonic 3.6 Tops TTS Leaderboards at Nearly 3x Speed(3 posts)→
More from Multimodal
- Generating 1 minute of AI video equals processing 60k words — HaktanSuren · 2026-08-18
- Short film 'FARMS' created with Grok Imagine and Runway, set in 2049 South Africa — bennash · 2026-08-18
- Fal hosts all Topaz Labs models with 16 enhancement endpoints for media — OdinLovis · 2026-08-18
- Grok 4.6 Used to Generate Characters for Sub8 — Daniel_Farinax · 2026-08-18
- Open-Sourced 3D World Prototype 'Sun Temple' Bundles Architecture, Animation and VFX with Live Demo — techartist_ · 2026-08-18
- Performance Analysis of Mixing RTX 3080 and A2000 for Stable Diffusion — djekler · 2026-08-18