There's a new benchmark for voice AI and we're at the top of both!
-- Sonic 3.5 : #1 text-to-speech on Artificial Analysis
-- Ink 2: #1 streaming ASR on Artificial Analysis
And if you want to be part of the team building this, we're hiring! Links in the comment! #Cartesia
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.
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.
Cartesia Ink-2 debuts as #1 for accuracy on the brand-new streaming speech-to-text leaderboard from @ArtificialAnlys! We designed Ink-2 from the ground up for voice agents - with low latency, eager transcripts, and semantic endpointing.
Sonic 3.5 is now the #1 text to speech model on the @ArtificialAnlys leaderboard!
You no longer have to trade off quality and latency - Sonic 3.5 also has the fastest time to first audio at 82ms end to end.
See full benchmark results 👇
Cartesia’s Sonic-3.5 takes the #1 spot on the Artificial Analysis Speech Arena Leaderboard, surpassing Inworld Realtime TTS 1.5 Max and Google’s Gemini 3.1 Flash TTS
Sonic-3.5 is the latest TTS model from @cartesia . It supports 42 languages, including 9 Indian languages, with 500+ voices available out of the box. The model has been highly preferred among voters in the TTS Arena, with its demonstrated naturalness and accurate transcript following.
Key takeaways:
➤ Quality: Sonic-3.5 has an Elo score of 1,218 (+16/-16) based on 1,144 arena appearances, placing it ahead of Inworld Realtime TTS 1.5 Max at 1,194 and Gemini 3.1 Flash TTS at 1,209
➤ Pricing: Sonic-3.5 is priced at $39/1M characters, a premium compared to Gemini 3.1 Flash TTS at $18.3/1M characters, and Inworld Realtime TTS 1.5 Max at $35/1M characters
➤ Speed: 105.5 characters per second, compared to 205 characters per second for Inworld Realtime TTS 1.5 Max and 26.3 characters per second for Gemini 3.1 Flash TTS
See more details and listen to samples below 🧵
@IndiGo6E@IndiGo6E we requested shambo to cancel our flight but he declined saying the flight is boarding in 5 minutes. That was half an hour back and the flight is delayed again. Please refund our amount immediately.
@IndiGo6E 6e 838 was delayed 3 hours with 3 gate changes. No meals, no compensation. It was scheduled to land at 10:25pm but now it will land at 1:00am. This was a horrible experience from a company boasting about their on-time performance. I want to be compensated for this.
@IndiGo6E The on ground support manager - Shambu, has very rudely said that we can cancel the flight if we want a refund but since it’s a conencting flight, we’re unable to do so. No assistance is being provided on ground.
@IndiGo6E Also, FYI - the flight is further delayed to 11:30pm. We don’t think it will even fly at 11:30 because it is 10:50 already and boarding has not even begun
@IndiGo6E Laurette, the food is provided at a different floor of the airport which is a 15 min walk. This was a connecting flight. We have been travelling for 15+ hours, so the 3 gate changes then again going to a different floor for food is really inconvenient.