IA
Inworld AI
Speech model ·May 2026

Inworld Realtime TTS-2

Speech Proprietary

About Inworld Realtime TTS-2

Inworld Realtime TTS-2 is an AI model developed by Inworld AI, in the speech category, released in 2026, made available as a proprietary (API-only) model. A closed-loop, conversation-aware voice model (research preview) that conditions on the full audio of prior turns rather.

On this page you'll find Inworld Realtime TTS-2's full specifications. Review provider pricing and benchmark scores below, or compare Inworld Realtime TTS-2 head-to-head with other speech models.

Community

Would you run Inworld Realtime TTS-2 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 Inworld Realtime TTS-2

Frequently asked questions

What is Inworld Realtime TTS-2?

A closed-loop, conversation-aware voice model (research preview) that conditions on the full audio of prior turns rather It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Inworld Realtime TTS-2?

Inworld Realtime TTS-2 was developed by Inworld AI and released in 2026.

Is Inworld Realtime TTS-2 open source or proprietary?

Inworld Realtime TTS-2 is a proprietary model. It is accessed through an API rather than by downloading the weights.

How much does Inworld Realtime TTS-2 cost?

Pricing for Inworld Realtime TTS-2 depends on the provider. See the providers table on this page for the latest API rates.

How does Inworld Realtime TTS-2 perform on benchmarks?

Benchmark scores for Inworld Realtime TTS-2 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 Inworld Realtime TTS-2?