Cartesia
Cartesia
Speech model · United States ·Jun 2026

Sonic-3.5

Speech Proprietary

About Sonic-3.5

Sonic-3.5 is an AI model developed by Cartesia, in the speech category, released in 2026, made available as a proprietary (API-only) model. Cartesia's flagship real-time streaming text-to-speech model, moved to general availability out of preview. Built on a s.

On this page you'll find Sonic-3.5's full specifications. Review provider pricing and benchmark scores below, or compare Sonic-3.5 head-to-head with other speech models.

Community

Would you run Sonic-3.5 again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

More models like Sonic-3.5

Frequently asked questions

What is Sonic-3.5?

Cartesia's flagship real-time streaming text-to-speech model, moved to general availability out of preview. Built on a s It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Sonic-3.5?

Sonic-3.5 was developed by Cartesia and released in 2026.

Is Sonic-3.5 open source or proprietary?

Sonic-3.5 is a proprietary model. It is accessed through an API rather than by downloading the weights.

How much does Sonic-3.5 cost?

Pricing for Sonic-3.5 depends on the provider. See the providers table on this page for the latest API rates.

How does Sonic-3.5 perform on benchmarks?

Benchmark scores for Sonic-3.5 are listed on this page as they are published. You can compare it head-to-head with other models on the GenAIList compare tool.

No videos yet. Know a good one? Add it below.

Know a great video about Sonic-3.5?