Simple Audio Transcription
Upload your audio file
Recipient email address:
Select Whisper model:
ggml-medium.bin (default)
ggml-small.bin
ggml-large-v3.bin
Model information:
ggml-medium:
~1.5 GB RAM, good accuracy, fast
ggml-small:
~2–3 GB RAM, solid and faster
ggml-large-v3:
~12–14 GB RAM, highest accuracy, slower
Choose audio file:
Start transcription