Sherpa-ONNX

Non-Streaming Speech Recognition from Microphone

Captures microphone audio, uses VAD to detect speech segments, then recognizes each segment with an offline ASR model.

Source code

Loading devices...Start RecordingStop RecordingClear⚙

Recording...00:00

Recognition Results

Copy TextCopy with TimeExport SRTSave All Audio

Start	End	Duration	Text

VAD & Recognizer Settings

VAD Threshold (0.0 – 1.0) Min Silence Duration (s) Min Speech Duration (s) Max Speech Duration (s) Recognizer Threads (1 – 16) ApplyCancel