“The following recording is in English.”
A pre-recorded TTS clip is prepended once per session to anchor language detection. The primer text is stripped from emitted transcripts.
Loading...
Loading...
Whisper-class ASR running on Apple Silicon. Direct WebSocket from your browser.
“The following recording is in English.”
A pre-recorded TTS clip is prepended once per session to anchor language detection. The primer text is stripped from emitted transcripts.
Press Start and speak. Partial results stream here in real time.