Search
Inworld Unveils Budget-Friendly, Low-Latency Speech Synthesis Model: TTS-1.5
2026-01-22 /
Read about 0 minute
Author：小编
PingWest, January 22 – As per a GlobeNewswire report, AI firm Inworld has officially rolled out its text-to-speech model, TTS-1.5. This innovative model is capable of producing natural, expressive speech in real-time, catering to a variety of languages. Notably, it boasts a real-time latency of under 250 milliseconds. Moreover, its usage cost is roughly $0.005 per minute, rendering it 25 times more economical than comparable offerings in the market.
-
C114 Communication Network -
Communication Home
7 X 24 Track global technological trends
