# Inworld TTS-1.5: Upgrading the #1 Ranked TTS Model with Production-Grade Latency, Expression and Stability

*Source* · `src-inworld-2026-tts-1-5` · status: **n/a**

| field | value |
|---|---|
| kind | Technical report / blog |
| authors | Inworld AI |
| venue | Inworld blog |
| date | 2026-01-21 |
| url | https://inworld.ai/blog/introducing-inworld-tts-1-5 |
| accessed | 2026-10-24 |

## Notes

TTS-1.5 Max: P90 time to first audio under 250 ms, $25 per 1M characters (about $0.025 per minute). TTS-1.5 Mini: under 130 ms, $15 per 1M characters (about $0.015 per minute). 15 languages. Vendor figures.

## Backlinks (computed)

**cited by:** [Realtime speech-to-speech and expressive TTS for characters](../technique/realtime-voice-models.md)

## Citation

Inworld AI (2026-01-21). *Inworld TTS-1.5: Upgrading the #1 Ranked TTS Model with Production-Grade Latency, Expression and Stability*. Inworld blog https://inworld.ai/blog/introducing-inworld-tts-1-5

---
Provenance: created in run `2026-10-24-techniques-llm-agents`.