Inworld's two TTS models rank high on time to first audio
What happened
Inworld says its Realtime TTS-2 and Realtime TTS-2 Flash rank near the top of Artificial Analysis' 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 that for real-time consumer applications, low latency matters as much as voice quality, and it included links to the full leaderboard and methodology. The rankings and latency figures above come from Inworld's own statements.
AI-written from the coverage · updated 4 d ago
Coverage timeline
Follow the coverage to see the story from different sides.
- Inworld AIPickInworld Realtime TTS-2 and TTS-2 Flash rank near the top of Artificial Analysis Time to First Audio benchmark
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.
Heat trend for this story
- Current (comparable)
- 3
- Peak (comparable)
- 10Nov 18 04:00
- 24-hour change
- -51%
The trend only compares participants observed continuously and completely, so it may cover fewer than the current heat count. Hover over or tap the chart to see each hour's heat; with a keyboard, use the left and right arrow keys.