From 5c3df0a434059bd0d541bda35a51e49e3c44dd55 Mon Sep 17 00:00:00 2001 From: historia Date: Thu, 20 Aug 2026 22:58:52 -0400 Subject: feat: experimental support for non-qwen models --- audiobook.py | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) (limited to 'audiobook.py') diff --git a/audiobook.py b/audiobook.py index 0b3734c..a984a0a 100755 --- a/audiobook.py +++ b/audiobook.py @@ -4,8 +4,6 @@ Qwen-Based Audiobook Converter Converts TXT, PDF and EPUB files into audiobooks using a local Qwen3-TTS server. Edit converter/config.py to change voice and processing settings. - -License: MIT """ import argparse @@ -89,7 +87,10 @@ Examples: metavar="LANG", help=("Output language for the synthesized speech, e.g. English, Japanese, " "or Auto (language names and short codes like en/ja are accepted). " - "Defaults to the LANGUAGE setting in converter/config.py (English).") + "With --backend audiocpp the language is adapted to the model " + "family: sent as a code (e.g. 'en') for families that take one, or " + "omitted when the model detects the language itself. Defaults to " + "the LANGUAGE setting in converter/config.py (English).") ) parser.add_argument( @@ -120,8 +121,10 @@ Examples: default=config.BACKEND, help=("TTS server to talk to: the Qwen3-TTS Gradio demos (gradio), the " "faster-qwen3-tts OpenAI-compatible server (faster), or an " - "audio.cpp audiocpp_server (audiocpp). Defaults to the BACKEND " - "setting in converter/config.py (gradio).") + "audio.cpp audiocpp_server (audiocpp) hosting any of its TTS " + "model families — Qwen3-TTS, Higgs Audio, VoxCPM2, IndexTTS2, " + "and more. Defaults to the BACKEND setting in " + "converter/config.py (gradio).") ) parser.add_argument( @@ -132,9 +135,10 @@ Examples: help=("Voice to request from a server-side voice configuration. faster: " "a key in the server's voices.json ('default' when it was started " "with --ref-audio). audiocpp: a voice_preset or voice_dir entry " - "(cloning); without this flag the audiocpp backend uses a built-in " - "CustomVoice speaker instead. Not used by the gradio backend " - "(use converter/config.py SPEAKER or --clone there).") + "(cloning); required for audio.cpp families without built-in " + "speakers (everything except Qwen3-TTS CustomVoice). Not used by " + "the gradio backend (use converter/config.py SPEAKER or --clone " + "there).") ) parser.add_argument( -- cgit v1.2.3