aboutsummaryrefslogtreecommitdiff
path: root/converter/config.py
diff options
context:
space:
mode:
authorhistoria <historiavg@proton.me>2026-08-20 22:58:52 -0400
committerhistoria <historiavg@proton.me>2026-08-20 22:58:52 -0400
commit5c3df0a434059bd0d541bda35a51e49e3c44dd55 (patch)
tree1d18e5f41ed9fc1184275a2a2b1a6555dffa4dc4 /converter/config.py
parent0c197324f5444b448c285d2a57bd0a5834c2fc84 (diff)
downloadtts-audiobook-generator-5c3df0a434059bd0d541bda35a51e49e3c44dd55.tar.gz
feat: experimental support for non-qwen models
Diffstat (limited to 'converter/config.py')
-rw-r--r--converter/config.py10
1 files changed, 9 insertions, 1 deletions
diff --git a/converter/config.py b/converter/config.py
index 83778ab..5cf4a8f 100644
--- a/converter/config.py
+++ b/converter/config.py
@@ -54,6 +54,14 @@ FASTER_VOICE = "default"
###############################################################################
AUDIOCPP_API_URL = "http://127.0.0.1:8080" # audio.cpp audiocpp_server
-# Model ids in the audio.cpp server.json config.
+# Model ids in the audio.cpp server.json config. AUDIOCPP_MODEL_ID may point
+# at any TTS model entry the server hosts (qwen3_tts, higgs_audio_tts,
+# voxcpm2, index_tts2, ...); the family is detected from the server at
+# startup and adapts the request automatically. Only qwen3_tts has built-in
+# speakers (speaker mode); every other family needs --voice with a
+# server-side voice preset. For single-model servers, set
+# AUDIOCPP_CLONE_MODEL_ID to the same id as AUDIOCPP_MODEL_ID (or leave it
+# empty); for Qwen3-TTS it typically names a second entry with the Base
+# (cloning) model.
AUDIOCPP_MODEL_ID = "qwen"
AUDIOCPP_CLONE_MODEL_ID = "qwen-clone"