zib/Veskslop-t
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Let word mode combine with the VOX preset

Browse Source
This commit is contained in:
Fisto
2026-09-21 11:47:38 +02:00
parent 7ad0a691db
commit 51d42b3a16
6 changed files with 44 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files
microslopsam/setup/test-wrapper.sh
+16
View File
@@ -103,6 +103,22 @@ VESKSLOP_TTS_VOICE=keith-bell run_wrapper
check "plain run writes both hives" "2" "$(grep -c 'Speakers\\{11260610' "$STUB_REG")"
check "plain run has no preset extras" "0" "$(grep -cE 'Gender|Line Mode|Default Speaker' "$STUB_REG")"
# Word mode combines with a preset and skips the VOX parser, with tags per word.
VESKSLOP_TTS_VOICE=keith-bell VESKSLOP_TTS_PRESET=vox VESKSLOP_TTS_VOX=1 \
VESKSLOP_TTS_WORDS=1 VESKSLOP_TTS_WORD_GAP_MS=0 VESKSLOP_TTS_SPEED=1.25 run_wrapper
check "word mode with preset synthesizes every word" "3" "$(grep -c '^ARGV:' "$STUB_LOG")"
check "word mode skips the VOX parser" "0" "$(grep -c 'wH1' "$STUB_LOG")"
check "word mode tags every word" "3" \
"$(sed -n 's/.*\[-t\] \[\(.*\)\] \[-o\].*/\1/p' "$STUB_LOG" | grep -c '^\\!R0.800 ')"
check "word mode keeps the preset profile" "2" "$(grep -c '"Pitch"=dword:00000003' "$STUB_REG")"
check "word mode emits no attributes" "0" "$(attr_count)"
# The vox preset implies VOX when the variable is unset, but word mode still wins.
VESKSLOP_TTS_VOICE=keith-bell VESKSLOP_TTS_PRESET=vox VESKSLOP_TTS_WORDS=1 \
VESKSLOP_TTS_WORD_GAP_MS=0 run_wrapper
check "implied VOX yields to word mode" "3" "$(grep -c '^ARGV:' "$STUB_LOG")"
check "implied VOX skipped for words" "0" "$(grep -c 'wH1' "$STUB_LOG")"
# Voice metadata follows the active preset.
check "voices reflect hev" "1" \
"$(VESKSLOP_TTS_PRESET=hev sh "$WRAP" --voices | tr ',' '\n' | grep -c 'keith-bell|Keith Bell|male|en|expression=59+defaults=pitch:15:rate:24')"
microslopsam/setup/veskslop-tts.sh
+9 -5
View File
@@ -16,7 +16,8 @@
# prominences, head_size, lowering
# VESKSLOP_TTS_HIGHPASS high-pass Hz (40-400, default 40)
# VESKSLOP_TTS_ECHO mono echo amount 0-100 (default 0)
# VESKSLOP_TTS_WORDS 1 = synthesize each word, merge (Flextalk)
# VESKSLOP_TTS_WORDS 1 = synthesize each word, merge (Flextalk);
# combines with a preset and wins over VOX prosody
# VESKSLOP_TTS_WORD_GAP_MS silence between words in ms (0-500)
# VESKSLOP_TTS_PRESET vox | hev (Keith Bell profile preset; vox implies VOX)
# VESKSLOP_TTS_VOX 1 = VOX prosody, NetTTS-style (Flextalk)
@@ -305,9 +306,11 @@ fi
# SAPI4 is ANSI/CP1252. VOX mode (Flextalk only) first transforms the text into
# vendor tags (\!wH1/\!wH0, \!br, \!sfNN) with setup/vox_parser.py; the parser
# works on UTF-8, so it runs before the CP1252 transliteration.
# works on UTF-8, so it runs before the CP1252 transliteration. Word mode builds
# its own cadence from single-word instances, so the parser is skipped there: the
# VOX tags cannot survive a word split.
TEXT_SRC="$TEXT_IN"
if [ "$VOX" = "1" ] && [ -n "$SPEAKER_GUID" ]; then
if [ "$VOX" = "1" ] && [ -n "$SPEAKER_GUID" ] && [ "$WORDS" != "1" ]; then
if command -v "$MICROSLOP_PYTHON" >/dev/null 2>&1 && [ -f "$MICROSLOP_ROOT/setup/vox_parser.py" ]; then
if [ "$VOX_CLEAN" = "1" ]; then
"$MICROSLOP_PYTHON" "$MICROSLOP_ROOT/setup/vox_parser.py" --clean < "$TEXT_IN" > "$TMP/vox.txt"
@@ -356,8 +359,9 @@ try_run_host() {
# Word mode (Flextalk): synthesize each word and merge with silence gaps, which
# gives the staccato radio cadence the Half-Life VOX/HEV voices are known for.
# VOX mode takes precedence: it produces its own cadence with vendor tags.
if [ "$WORDS" = "1" ] && [ -n "$SPEAKER_GUID" ] && [ "$VOX" != "1" ]; then
# It combines with a preset (the profile is already written) and takes precedence
# over VOX prosody, which cannot survive a word split.
if [ "$WORDS" = "1" ] && [ -n "$SPEAKER_GUID" ]; then
GAP=$WORD_GAP
case "$GAP" in *[!0-9]*|"") GAP=120 ;; esac
[ "$GAP" -gt 500 ] && GAP=500