Audio Transcription
Transcribe audio and video files with speaker identification. Runs locally on your machine.
Run
sdexe transcribe in your terminal or pip install sdexe[transcribe] to enable this feature.
or drop a file here · MP3, WAV, M4A, FLAC, MP4, MKV, and more
Required for speaker diarization model. Get token
Speaker identification unavailable. Install pyannote.audio for diarization.