AssemblyAI-TTS-1 tops TTS speed at 162 chars/sec as Artificial Analysis refreshes leaderboards
ArtificialAnlys · x · 2026-10-29
Artificial Analysis refreshed its Text-to-Speech leaderboards. On speed, AssemblyAI-TTS-1 leads at 162 chars/sec, ahead of Cartesia Sonic 3.6 (148.6), Mistral Voxtral 3 TTS (112.3), Speechify Simba 3.2 (84.9), ElevenLabs Eleven v4 (75.1) and Google Gemini 3.8 Flash TTS (53.4). At $15/1M chars it also undercuts Gemini 3.8 Flash TTS ($16.5), Qwen-Audio-3.1-TTS-Plus ($19.3) and Breeze TTS 2 ($34). On arena Elo, Eleven v4 (1335) and v4 Turbo (1333) lead, followed by Qwen-Audio-3.1-TTS-Plus (1305), Sonic 3.6 (1294) and Gemini 3.8 Flash TTS (1283).
More from Multimodal
- Open-source TTS model Phonon hits ~85k downloads in a week, Rust inference stack — mattturck · 2026-10-29
- Higgsfield wrapper drama: user rebuilds AI person-swap video workflow in 30 minutes — ravisparikh · 2026-10-29
- CapCut Halloween Sale: Pro Up to 60% Off, Dreamina for $0.29 — FellMentKE · 2026-10-29
- HeyGen launches Voice STS, transferring pauses and whispers to your avatar — HeyGen · 2026-10-29
- Run Lola Run Director Tom Tykwer Now Shooting Films With Seedance, 'Directability' Is the New Moat — LinusEkenstam · 2026-10-29
- Dev vibecodes a ComfyUI node that auto-archives and organizes all your generations — LaurentLaSalle · 2026-10-29