Skip to content
Inworld AI· inworld·· 4 d agoPickAI score42

Inworld Realtime TTS-2 and TTS-2 Flash rank near the top of Artificial Analysis Time to First Audio benchmark

Inworld Realtime TTS-2 and Realtime TTS-2 Flash sit near the top of @ArtificialAnlys's new Time to First Audio (TTFA) benchmark.

AI summary

Inworld's Realtime TTS-2 and Realtime TTS-2 Flash rank near the top of Artificial Analysis's newly released Time to First Audio (TTFA) benchmark, with average latencies of 181ms and 86ms respectively. The benchmark measures how quickly a model begins outputting audible speech; Inworld says low latency matters as much as speech quality for real-time consumer applications, and included links to the full leaderboard and methodology.

Why it matters

The source gives the average latency figures for the two speech models on a third-party TTFA benchmark, which can be compared against the speech response speeds of other models.

Source: Inworld AI · x.com