---
id: "2026-08-31-inworld-realtime-tts-2"
url: "https://postcutoff.com/e/2026-08-31-inworld-realtime-tts-2/"
as_of: "2026-11-13T13:49:00+01:00"
date: "2026-08-31"
date_precision: day
category: model-release
importance: 3
confidence: high
status: [Confirmed]
sources: 5
editor: human editor
human_review: null
version: "2026-10-04"
---

As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/e/2026-08-31-inworld-realtime-tts-2/

# Inworld Realtime TTS-2 reaches GA with audio-aware, prompt-directed speech

Inworld AI made Realtime TTS-2 (`inworld-tts-2`) and TTS-2 Flash generally available on 2026-08-31 after a research preview on 2026-05-05. TTS-2 conditions on the actual audio of earlier turns, so it can pick up a user's tone and pacing. It takes plain-English voice direction and keeps one voice identity across 100+ languages, at $25 (Flash $15) per 1M characters pay-as-you-go.

## Key facts
- Oct 1, 2026: Inworld acquired Ultravox, a platform for building real-time voice agents (turn-taking, interruptions); Ultravox customers get Realtime TTS-2; terms not disclosed
- Model id inworld-tts-2; endpoint POST https://api.inworld.ai/tts/v1/voice
- TTS-2 median TTFA <200 ms; Flash ~20 ms TTFB (docs)
- Voice cloning from 5-15 s; voice design from text; STABLE/BALANCED/CREATIVE modes
- Artificial Analysis 29 Sept 2026: #5 (Elo 1244); Inworld's earlier TTS 1.5 had been #1
- TTS-1..1.5 discontinued 2026-06-15; Inworld also offers migration from shut-down PlayHT

## What happened

Inworld promoted TTS-2 from research preview to GA and added a Flash variant for latency- and cost-sensitive agents.

## Why it matters

TTS-2 closes the loop between listening and speaking in a cascaded voice stack: the TTS hears the user, not just the transcript. The price is also well under ElevenLabs' list price.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): 123 days after its cutoff
- Claude Opus 5.5 (training cutoff June 2026): 62 days after its cutoff
- Gemini 4 Hydrogen (training cutoff March 2026): 153 days after its cutoff
- Grok 4.7 (training cutoff May 2026): 92 days after its cutoff

## Sources

1. [Inworld: Realtime TTS-2](https://inworld.ai/blog/realtime-tts-2) (inworld.ai, official)
2. [Inworld docs: TTS models](https://docs.inworld.ai/tts/tts-models) (docs.inworld.ai, docs)
3. [Inworld pricing](https://inworld.ai/pricing) (inworld.ai, official)
4. [Yahoo Finance: AI research lab Inworld acquires Ultravox](https://finance.yahoo.com/technology/ai/articles/ai-research-lab-inworld-acquires-211500825.html) (finance.yahoo.com, press)
5. [MarkTechPost: preview launch (2026-05-05)](https://www.marktechpost.com/2026/05/05/inworld-ai-launches-realtime-tts-2-a-closed-loop-voice-model-that-adapts-to-how-you-actually-talk/) (marktechpost.com, press)

## Changes

- 2026-10-03: Added the Ultravox acquisition (Oct 1)
- 2026-09-29 (filed): Created

## Related

- 2026-09-28: [ElevenLabs launches Eleven v4 and Eleven v4 Turbo, #1 on Artificial Analysis TTS arena](https://postcutoff.com/e/2026-09-28-elevenlabs-eleven-v4/index.md)
- 2026-08-27: [Cartesia Sonic-3.6 goes GA and tops the Artificial Analysis Speech Arena](https://postcutoff.com/e/2026-08-27-cartesia-sonic-3-6/index.md)
- Models: [Inworld Realtime TTS-2 / TTS-2 Flash](https://postcutoff.com/m/inworld-tts-2/) (`inworld-tts-2`)