zib/MicroslopSam
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

wrapper: leading low hum to prime Discord (configurable MS/HZ/DB)

Browse Source
This commit is contained in:
Fisto
2026-09-16 13:21:41 +02:00
parent f9f1c454d5
commit 1f77dfba64
4 changed files with 47 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
setup/veskslop-tts.sh
+29 -1
View File
@@ -20,6 +20,9 @@
# VESKSLOP_TTS_WORD_GAP_MS silence between words in ms (0-500)
# VESKSLOP_TTS_VOX 1 = VOX prosody, NetTTS-style (Flextalk)
# VESKSLOP_TTS_VOX_CLEAN 1 = VOX without the \!wH1/\!wH0 stutter
# VESKSLOP_TTS_HUM_MS leading low hum in ms, 0 = off (default 80)
# VESKSLOP_TTS_HUM_HZ hum frequency, 30-200 (default 75)
# VESKSLOP_TTS_HUM_DB hum peak level, -80..-6 (default -48)
#
# Output: 48 kHz mono s16le WAV, trimmed, faded, loudness-normalized.
set -eu
@@ -52,6 +55,9 @@ WORDS=${VESKSLOP_TTS_WORDS:-0}
WORD_GAP=${VESKSLOP_TTS_WORD_GAP_MS:-120}
VOX=${VESKSLOP_TTS_VOX:-0}
VOX_CLEAN=${VESKSLOP_TTS_VOX_CLEAN:-0}
HUM_MS=${VESKSLOP_TTS_HUM_MS:-80}
HUM_HZ=${VESKSLOP_TTS_HUM_HZ:-75}
HUM_DB=${VESKSLOP_TTS_HUM_DB:--48}
case "$VOICE" in
sam) ENGVOICE="Sam" ;;
@@ -377,7 +383,29 @@ else
fi
TMPOUT="$TMP/out.wav"
if ! "$MICROSLOP_FFMPEG" -hide_banner -nostats -y -i "$RAW" -af "$PRE,volume=${GAIN}dB" \
# Leading hum: a quiet low tone in the pre-speech padding, to prime Discord's
# audio pipeline so the first syllable is not gated. Level/frequency/duration
# are configurable; 0 ms disables it.
case "$HUM_MS" in *[!0-9]*|"") HUM_MS=80 ;; esac
[ "$HUM_MS" -gt 2000 ] && HUM_MS=2000
case "$HUM_HZ" in *[!0-9.]*|"") HUM_HZ=75 ;; esac
case "$HUM_DB" in *[!0-9.-]*|""|"."|"-") HUM_DB=-48 ;; esac
if [ "$HUM_MS" -gt 0 ]; then
HUM_S=$(awk -v ms="$HUM_MS" 'BEGIN{printf "%.3f", ms/1000}')
HUM_HZ=$(awk -v v="$HUM_HZ" 'BEGIN{ if (v<30) v=30; if (v>200) v=200; printf "%.1f", v }')
HUM_DB=$(awk -v v="$HUM_DB" 'BEGIN{ if (v>-6) v=-6; if (v<-80) v=-80; printf "%.1f", v }')
HUM_AMP=$(awk -v db="$HUM_DB" 'BEGIN{printf "%.6f", 10^(db/20)}')
HUM_FADE=$(awk -v s="$HUM_S" 'BEGIN{ f=s/4; if (f>0.02) f=0.02; if (f<0.005) f=0.005; printf "%.3f", f }')
HUM_FADE_OUT=$(awk -v s="$HUM_S" -v f="$HUM_FADE" 'BEGIN{printf "%.3f", s-f}')
if ! "$MICROSLOP_FFMPEG" -hide_banner -nostats -y \
-f lavfi -i "aevalsrc=exprs='$HUM_AMP*sin(2*PI*$HUM_HZ*t)':s=48000:d=$HUM_S" \
-i "$RAW" \
-filter_complex "[0:a]afade=t=in:st=0:d=$HUM_FADE,afade=t=out:st=$HUM_FADE_OUT:d=$HUM_FADE,aformat=sample_fmts=s16:channel_layouts=mono:sample_rates=48000[h];[1:a]$PRE,volume=${GAIN}dB,aresample=48000,aformat=sample_fmts=s16:channel_layouts=mono[a];[h][a]concat=n=2:v=0:a=1[out]" \
-map "[out]" -c:a pcm_s16le "$TMPOUT" >/dev/null 2>"$TMP/ff"; then
head -c 400 "$TMP/ff" >&2
exit 1
fi
elif ! "$MICROSLOP_FFMPEG" -hide_banner -nostats -y -i "$RAW" -af "$PRE,volume=${GAIN}dB" \
-ar 48000 -ac 1 -c:a pcm_s16le "$TMPOUT" >/dev/null 2>"$TMP/ff"; then
head -c 400 "$TMP/ff" >&2
exit 1