Skip to content
AI News HubLIVE
More
Summary only

Inworld AI Launches Realtime TTS-2: A Closed-Loop Voice Model That Adapts to How You Actually Talk

Inworld AI has released Realtime TTS-2, a new voice model that operates as a closed-loop system, taking full audio context of the conversation rather than just transcripts, to understand user tone, pacing, and emotion. Key features include natural language voice direction, crosslingual support across 100+ languages, advanced voice design without reference audio, and natural disfluencies. The model is available as a research preview via Inworld API and ranks #1 on the Artificial Analysis Speech Arena.

SourceMarkTechPostAuthor: Asif Razzaq
Inworld AI Launches Realtime TTS-2: A Closed-Loop Voice Model That Adapts to How You Actually Talk
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions

Summary only

Under the source content permission, this page provides an editorial summary, key points, and a link to the original article.

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Closed-loop architecture: Model takes full audio of prior turns as input, capturing tone, pacing, and emotional state beyond transcripts.
  • Voice direction: Developers can steer delivery using plain-language prompts like [speak sadly] and include non-verbal markers such as [laugh] or [sigh].
  • Crosslingual support: Single voice identity preserved across 100+ languages, with mid-utterance language switching without flags.
  • Advanced voice design: Generate and save a voice from a written prompt with no reference audio, offering three stability modes.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Tools