Real-time speech recognition powered by relax.ai and NVIDIA.
Microphone access requires a secure context. Since this site uses HTTP, you need to enable it in your browser settings.
chrome://flags/#unsafely-treat-insecure-origin-as-secureabout:configmedia.getusermedia.insecure.enabled| Metric | Description |
|---|---|
| RTFx | Real-Time Factor — how many times faster than real-time. Higher is better (e.g., 10x means 1 second of audio processed in 0.1 seconds) |
| Latency | Time from sending audio to receiving transcription |
| TTFW | Time To First Word — delay from speech start to first transcription |
| E2E | End-to-End latency — total time from speech start to final transcription |