AA Provider Voice TTS Arena ↗Unversioned · provider native voices
1,262Provider native voices · all categories · US + UK accents · 8 listed voices
95% CI 1,247–1,277 · n=1,988
inworld-aiReleased Aug 31, 2026
realtime-tts-2
Realtime TTS 2.0 is a low-latency text-to-speech model with natural language steering, allowing you to control tone and emotion directly in the prompt (e.g., “[be happy and upbeat] Hello!”). It supports…
Source description
Realtime TTS 2.0 is a low-latency text-to-speech model with natural language steering, allowing you to control tone and emotion directly in the prompt (e.g., “[be happy and upbeat] Hello!”). It supports cross-lingual voices and multiple languages, enabling the same voice to speak consistently across different languages. This is an early access preview ahead of full launch, with ongoing improvements to voice quality and steering.
Provider endpoints1
Benchmark results1
Measured performance
All leaderboards ↗Benchmark results
Access & cost
1 quotePrices across providers
DeepInfra
1,000 input characters
- Rate
- $0.035
Model specifications
- Developer
- inworld-ai
- Modality
- Audio
- Context
- Not reported
- Maximum output
- Not reported
- Weights
- Not reported
- Released
- Aug 31, 2026
- Provider listed
- May 4, 2026
- First discovered
- Oct 16, 2026
Exact identities
- deepinfra
inworld-ai/realtime-tts-2 - aa-tts
359b0666-ac70-4eb2-9804-c2bd02e06f9a
Sources
Updated Oct 18, 2026
More from inworld-ai
View all ↗inworld-aiListed May 4
realtime-tts-1.5-mini
Fast multilingual text-to-speech model by Inworld AI with 130+ preset voices across 15 languages. Supports voice cloning, word-level timestamps, and streaming. Optimized for low-latency applications with…
No reported score
No reported score
inworld-aiListed May 4
realtime-tts-1.5-max
High-quality multilingual text-to-speech model by Inworld AI with 130+ preset voices across 15 languages. Supports voice cloning, word-level timestamps, and streaming. Optimized for natural, expressive…
No reported score
No reported score