Inworld launches TTS-1.5 for real-time voice with 16 languages
SMRTR summary
Inworld released TTS-1.5, a new text-to-speech system designed for real-time voice applications that operates in 16 languages with ultra-low latency. The system comes in two versions - TTS-1.5-Max with 190ms median latency for most uses, and TTS-1.5-Mini with 120ms median latency for speed-critical applications. Both models are currently free through December 2025 before switching to usage-based pricing of $5-10 per million characters, positioning Inworld to compete directly with established voice AI providers.
SMRTR provides this summary for quick context. The original article belongs to Testing Catalog.
Read the original article