aboutsummaryrefslogtreecommitdiff
path: root/app/converter
diff options
context:
space:
mode:
authorhistoria <historiavg@proton.me>2026-08-25 13:28:42 -0400
committerhistoria <historiavg@proton.me>2026-08-25 13:28:42 -0400
commitd4dbc1a158d1dd6babcba7333a4ed7d719b65d3e (patch)
treeccba2efaef9a265f7cbc754cf70d8071d09e9612 /app/converter
parent0cc01d1da0a629e104202053feb0bb0db91d578d (diff)
downloadtts-audiobook-generator-d4dbc1a158d1dd6babcba7333a4ed7d719b65d3e.tar.gz
feat: automatically name audio.cpp model ids with long name
Diffstat (limited to 'app/converter')
-rw-r--r--app/converter/config.py27
1 files changed, 14 insertions, 13 deletions
diff --git a/app/converter/config.py b/app/converter/config.py
index 6eacb41..3caa1ab 100644
--- a/app/converter/config.py
+++ b/app/converter/config.py
@@ -63,19 +63,20 @@ AUDIOCPP_API_URL = "http://127.0.0.1:8080" # audio.cpp audiocpp_server
AUDIOCPP_REMOTE_URL = "http://127.0.0.1:8080" # externally-run audiocpp_server ("" disables probing)
# 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. A multi-model server (one server.json hosting several
-# lazily-loaded entries) does not need editing here: leave AUDIOCPP_MODEL_ID
-# unset to auto-select when only one entry is hosted, or pick the entry per
-# run with the --model CLI flag.
-AUDIOCPP_MODEL_ID = "qwen"
-AUDIOCPP_CLONE_MODEL_ID = "qwen"
+# at any TTS model entry the server hosts; 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. The server entry id is the model package's
+# target_directory name (e.g. "Qwen3-TTS-12Hz-1.7B-Base-GGUF"). 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. Both default to empty so a
+# single-entry server is auto-selected; a multi-model server (one server.json
+# hosting several lazily-loaded entries) needs no editing here either: leave
+# AUDIOCPP_MODEL_ID unset to auto-select when only one entry is hosted, or
+# pick the entry per run with the --model CLI flag.
+AUDIOCPP_MODEL_ID = ""
+AUDIOCPP_CLONE_MODEL_ID = ""
# Voice design / style instruction sent with every audio.cpp request when
# the --instructions CLI flag is not given. Required for server entries