Vibeleaderboard
← All Intel
Intel / post

Cartesia's Sonic 3.6 takes the #1 spot on both the Provider Voice and Controlled

Source
x.com
Date
Artificial Analysis@ArtificialAnlys

Cartesia's Sonic 3.6 takes the #1 spot on both the Provider Voice and Controlled Voice Artificial Analysis Speech Arena leaderboards, surpassing Speechify AI's Simba 3.2 and Alibaba's Qwen-Audio-3.0-TTS-Plus, with Sonic 3.5 holding #2 on Controlled Voice Sonic 3.6 is the latest TTS model from @cartesia, supporting 40+ languages including English, Hindi, Spanish, French, German and Japanese. In the TTS Arena, the model has been preferred by voters and has demonstrated natural speech and adaptive pacing across conversations. Key takeaways: ➤ Controlled Voice: Sonic 3.6 takes #1 on the Controlled Voice Arena with an Elo of 1,144 (+18/-18) across 1,339 appearances, ahead of Cartesia's own Sonic 3.5 at 1,099 and ElevenLabs' Eleven v3 at 1,060 ➤ Provider Voice: Sonic 3.6 also takes #1 on the Provider Voice Arena with an Elo score of 1,286 (+19/-19) based on 1,300 arena appearances, placing it ahead of Simba 3.2 at 1,238 and Qwen-Audio-3.0-TTS-Plus at 1,237 ➤ Pricing: At $49 per 1M characters via the Cartesia platform, Sonic 3.6 is the most expensive of the top three models on quality, roughly 5x Speechify AI's Simba 3.2 at $10 and nearly double Alibaba's Qwen-Audio-3.0-TTS-Plus at…

Read the full post on X

Context

Cartesia's Sonic 3.6 text-to-speech model is the voice voters preferred most on both of Artificial Analysis's Speech Arena leaderboards, Provider Voice and Controlled Voice, according to the firm's August 17 post. The arena turns voter preferences into Elo ratings. On Provider Voice, Sonic 3.6 scored 1,286 (plus or minus 19) across 1,300 appearances, ahead of Speechify AI's Simba 3.2 at 1,238 and Alibaba's Qwen-Audio-3.0-TTS-Plus at 1,237. On Controlled Voice it scored 1,144 (plus or minus 18) across 1,339 appearances, ahead of Cartesia's previous Sonic 3.5 at 1,099 and ElevenLabs' Eleven v3 at 1,060. In both cases the lead is more than twice the plus-or-minus range Artificial Analysis gives for Sonic 3.6's own score.

That preference comes at a price. At $49 per million characters on Cartesia's platform, Sonic 3.6 is the most expensive of the three top models on quality, by Artificial Analysis's count: roughly five times Simba 3.2 at $10 and nearly double Qwen-Audio-3.0-TTS-Plus at $27.59, though half the price of Eleven v3 at $100. It is also fast, generating 136.1 characters per second against 46.7 for Eleven v3 and 24.2 for Google's Gemini 3.1 Flash TTS; the post gives no speed figures for Simba 3.2 or Qwen-Audio. For developers picking a speech model, the result favors Sonic 3.6 where listener preference and speed justify the cost, while the next two Provider Voice models cost a fraction as much.

Terms in this piece · Glossary
  • benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
More from Artificial Analysis
Recommended reads
Comments

Checking sign-in…

Loading comments…