From 12caa5275c5d904c1451ea9b6ef9e7ad241d969a Mon Sep 17 00:00:00 2001 From: historia Date: Sun, 16 Aug 2026 20:32:00 -0400 Subject: readme --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index dca4d93..f03aa07 100644 --- a/README.md +++ b/README.md @@ -89,6 +89,8 @@ CUSTOM_VOICE_INSTRUCT = "Speak naturally and clearly, as if reading a dramatic b python audiobook_converter.py --voice-clone --voice-sample path/to/reference.wav ``` +The reference .wav should be ~10-15 seconds with a minimum of 3 seconds and maximum of 60 seconds. Longer is not better. ~15 seconds is ideal. + Omit `--voice-sample-text` and Whisper will be used automatically to transcribe the reference audio (`faster_whisper` or `whisper`). If no Whisper backend is installed, it falls back to x-vector-only cloning. To skip automatic transcription explicitly, pass `--no-transcription`. This should be worse, but in my experience may give a preferable flatter tone to certain voices. -- cgit v1.2.3