@krandiash: Our new TTS model Sonic-3.6 is now GA We went into preview last week as the #1 model on AA and it's been great to see e…
Summary
Cartesia's TTS model Sonic-3.6 is now generally available, having been rebuilt from the architecture up and receiving positive feedback from its preview phase.
View Cached Full Text
Cached at: 08/28/26, 05:46 AM
Our new TTS model Sonic-3.6 is now GA
We went into preview last week as the #1 model on AA and it’s been great to see early users back this up
Overwhelmingly positive feedback, so much so that we graduated 3.6 to GA within a week
And yes, the next model is cooking 🧑🍳
Cartesia (@cartesia): Sonic-3.6 is now generally available.
In January we made a bet: stop tuning the existing paradigm, rebuild from the architecture up.
How we topped our own best model in two months →
Similar Articles
@_albertgu: Extremely proud of the team @cartesia for launching Sonic 3.5, which sets a new state of the art for TTS I personally l…
Cartesia launches Sonic 3.5, a new state-of-the-art TTS model supporting 42 languages, taking the #1 spot on the Artificial Analysis Speech Arena Leaderboard.
@inworld_ai: Realtime TTS-2 is GA today, now the #1 model on Artificial Analysis and fastest TTS in the world of its class. The rese…
Inworld AI releases Realtime TTS-2 as generally available, claiming it to be the top model on Artificial Analysis and the fastest TTS in its class, representing a significant advancement in the company's history.
@_philschmid: Powered by Gemini 3.8 TTS.
Gemini Notebook announces that their AI hosts' sound has been updated using Gemini 3.8 TTS, indicating an improvement in text-to-speech capabilities.
@SamuelZengML: We’re genuinely surprised and grateful to see our latest open-source model, Audio8/Audio8-TTS-Preview-0.6b, reach #1 on…
Audio8's open-source TTS model reached #1 on Hugging Face's TTS trending list and #10 overall, with the team expressing gratitude and plans to keep improving.
@kwindla: OpenAI shipped a new speech-to-speech model today: gpt-realtime-2 This is the first speech-to-speech model good enough …
OpenAI has released gpt-realtime-2, a new speech-to-speech model optimized for real-time voice agent interactions with low-latency tool calling.