Sonic-3.5 surpassed ElevenLabs and OpenAI in blind listener votes.
We released Sonic-3.5 and Ink-2, the #1 streaming models for text to speech and speech to text you can use in your voice agents today.
New architectures enable new frontiers for speed and quality.
We're now the only provider to have #1 models for both speaking and listening.
Many users congratulated Cartesia on launching Sonic-3.5 and Ink-2 as top streaming TTS and STT models due to their benchmark-setting achievements, while a few dismissed the releases as unremarkable or worse.
No Digg Deeper questions have been answered for this story yet.
If you switch to Cartesia from your existing provider, three months are on us.
Hear the difference today. 👇🏻
We’ve seen incredible traction this year, with enterprises transforming every part of their operations with Voice AI. We’re sharing what we’ve learned and are giving away a guide to the top 10 enterprise use cases for Voice AI.
Retweet and comment "CARTESIA" on the main video and we'll send you the guide and $100 in credits so you can get started today.
Try a call with a real voice agent and sign up for the promo here!
https://cartesia.ai/launch?utm_source=twitter&utm_medium=social&utm_campaign=levelup25&ref=twitter
#1 again!
Cartesia Sonic 3.5 is the #1 streaming TTS model on Voice Arena US English Leaderboard.
In the overall leaderboard (streaming + non-streaming) it jumped from rank #9 → #2, moving ahead of Grok TTS, ElevenLabs v3 & OpenAI's gpt-4o-mini-tts.
Sonic-3.5 is the latest TTS model from @cartesia . It supports 42 languages, with 500+ voices available out of the box. The model has been highly preferred among raters on @voicearena_ai .
Results backed by 11,110 blind, head-to-head listener votes
@krandiash its so hard to make a text-to-speech model with such a sub-300ms median ttft (time to first token).
big big congrats!
@krandiash Making the word more magical, one model at a time.
Go Cartesia!
@krandiash Lol 11labs is so cooked, their speed is nothing compared to this
@krandiash Customer support has been running on Internet Explorer for years
@krandiash Incredible
@krandiash 82ms to first audio is genuinely insane. ElevenLabs Turbo is sitting at 250ms+. this is not close.
@krandiash Damn I just cloned my voice in da playground and it low-key sounds a lot like me. Took 30 seconds.
@krandiash Most voice agents sound fast or natural - never seen an agent do both
@krandiash Voice is quietly becoming one of the most important interfaces in AI.
@krandiash Are you guys compliant with India data residency requirements? If so, it'll be interesting to see adoption of these models in India
@chongz
@krandiash This upgrade is going to make my voice agents feel uncomfortably human🤯
@krandiash Voice agents are only as good as their weakest side. Either understanding or responding. Having #1 models for both is a serious advantage.
@krandiash why's the founder asking for business class?? broke behavior 💀
@krandiash does it handle Bengali and Marathi at the same quality as the English demo, because that is the difference between a fun toy and something we ship
@krandiash Congrats on the launch Karan and team! Looks great
