Sync wrapper with Veskslop: streaming/crunch modes, vox/hev voice IDs
The Veskslop integration copy had grown word streaming (VESKSLOP_TTS_STREAM, stream gain), 1990s crunch filters (VESKSLOP_TTS_CRUNCH[_BITS|_RATE]), echo timing/level, and first-class vox/hev voice IDs with preset-aware default metadata. Merge those back into the standalone repo, keeping the tuned VOX preset (pitch 0, rate 15, head size 34, lowering 50) in the preset and in the published defaults. Update the wrapper regression test to the tuned registry values, add __pycache__ to .gitignore, and document the new variables, voice IDs, placeholder set and the word-mode-over-VOX precedence in README, NOTES and TTS-DESIGN.
This commit is contained in:
Fisto
+173
-11
@@ -16,13 +16,24 @@
|
||||
# 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_ECHO_DELAY_MS echo delay 10-400 (default 60)
|
||||
# VESKSLOP_TTS_ECHO_LEVEL echo repeat level 0-0.95, relative to the
|
||||
# dry voice (default 0.85)
|
||||
# VESKSLOP_TTS_CRUNCH off | hl90 | hl90hq | telephone | adpcm | crush
|
||||
# (1990s lossy character, applied last)
|
||||
# VESKSLOP_TTS_CRUNCH_BITS 1-16, overrides the preset bit depth
|
||||
# VESKSLOP_TTS_CRUNCH_RATE 4000-48000 Hz, overrides the preset rate
|
||||
# VESKSLOP_TTS_STREAM 1 = word mode writes the WAV as it goes
|
||||
# VESKSLOP_TTS_STREAM_GAIN_DB fixed gain for streaming (no measurement)
|
||||
# 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_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)
|
||||
# voice `vox`/`hev` Half-Life profiles as first-class voices
|
||||
# VESKSLOP_TTS_PRESET vox | hev (Half-Life profiles, Keith Bell;
|
||||
# vox also enables VOX prosody)
|
||||
#
|
||||
@@ -33,11 +44,21 @@ HERE=$(CDPATH= cd -- "$(dirname -- "$0")" && pwd)
|
||||
. "$HERE/config.sh"
|
||||
ROOT=$MICROSLOP_ROOT
|
||||
|
||||
# The Keith Bell defaults follow the active preset so the UI's "default" snap points
|
||||
# match the values the preset actually writes.
|
||||
VOX_DEFAULTS="pitch:0:rate:15:prominences:22:head_size:34:lowering:50:expression:59"
|
||||
HEV_DEFAULTS="pitch:15:rate:24:prominences:22:head_size:52:lowering:40:expression:59"
|
||||
case "${VESKSLOP_TTS_PRESET:-}" in
|
||||
vox) KB_DEFAULTS="$VOX_DEFAULTS" ;;
|
||||
hev) KB_DEFAULTS="$HEV_DEFAULTS" ;;
|
||||
*) KB_DEFAULTS="pitch:27:rate:33:prominences:17:head_size:46:lowering:40:expression:59" ;;
|
||||
esac
|
||||
|
||||
# VESKSLOP_TTS_VOICES entries: id|Name|gender|language[|flags]
|
||||
# `expression=NN` marks a Flextalk voice with an Expression profile parameter and
|
||||
# its registry default. Expression is applied at voice load, so the wrapper writes
|
||||
# it into the Wine registry before synthesis.
|
||||
VOICES="sam|Sam|male|en,mary|Mary|female|en,mike|Mike|male|en,keith-bell|Keith Bell|male|en|expression=59+defaults=pitch:27:rate:33:prominences:17:head_size:46:lowering:40:expression:59,kerry-watson|Kerry Watson|female|en|expression=100+defaults=pitch:65:rate:32:prominences:17:head_size:45:lowering:40:expression:100,mike-telephone|Mike (for Telephone)|male|en,mary-telephone|Mary (for Telephone)|female|en,mike-hall|Mike in Hall|male|en,mike-stadium|Mike in Stadium|male|en,mike-space|Mike in Space|male|en,mary-hall|Mary in Hall|female|en,mary-stadium|Mary in Stadium|female|en,mary-space|Mary in Space|female|en"
|
||||
VOICES="sam|Sam|male|en,mary|Mary|female|en,mike|Mike|male|en,keith-bell|Keith Bell|male|en|expression=59+defaults=$KB_DEFAULTS,vox|VOX (Half-Life)|male|en|expression=59+defaults=$VOX_DEFAULTS,hev|HEV suit|male|en|expression=59+defaults=$HEV_DEFAULTS,kerry-watson|Kerry Watson|female|en|expression=100+defaults=pitch:65:rate:32:prominences:17:head_size:45:lowering:40:expression:100,mike-telephone|Mike (for Telephone)|male|en,mary-telephone|Mary (for Telephone)|female|en,mike-hall|Mike in Hall|male|en,mike-stadium|Mike in Stadium|male|en,mike-space|Mike in Space|male|en,mary-hall|Mary in Hall|female|en,mary-stadium|Mary in Stadium|female|en,mary-space|Mary in Space|female|en"
|
||||
|
||||
if [ "${1:-}" = "--voices" ]; then
|
||||
echo "$VOICES"
|
||||
@@ -53,11 +74,25 @@ EXPRESSION=${VESKSLOP_TTS_EXPRESSION:-${6:-}}
|
||||
PROFILE=${VESKSLOP_TTS_PROFILE:-}
|
||||
HIGHPASS=${VESKSLOP_TTS_HIGHPASS:-40}
|
||||
ECHO=${VESKSLOP_TTS_ECHO:-0}
|
||||
ECHO_DELAY=${VESKSLOP_TTS_ECHO_DELAY_MS:-60}
|
||||
ECHO_LEVEL=${VESKSLOP_TTS_ECHO_LEVEL:-0.85}
|
||||
CRUNCH=${VESKSLOP_TTS_CRUNCH:-off}
|
||||
CRUNCH_BITS=${VESKSLOP_TTS_CRUNCH_BITS:-}
|
||||
CRUNCH_RATE=${VESKSLOP_TTS_CRUNCH_RATE:-}
|
||||
STREAM=${VESKSLOP_TTS_STREAM:-0}
|
||||
STREAM_GAIN=${VESKSLOP_TTS_STREAM_GAIN_DB:-0}
|
||||
WORDS=${VESKSLOP_TTS_WORDS:-0}
|
||||
WORD_GAP=${VESKSLOP_TTS_WORD_GAP_MS:-120}
|
||||
VOX=${VESKSLOP_TTS_VOX:-0}
|
||||
VOX_CLEAN=${VESKSLOP_TTS_VOX_CLEAN:-0}
|
||||
PRESET=${VESKSLOP_TTS_PRESET:-}
|
||||
|
||||
# The Half-Life voices are Keith Bell with a fixed profile preset; selecting one
|
||||
# stands in for VESKSLOP_TTS_PRESET.
|
||||
case "$VOICE" in
|
||||
vox) [ -n "$PRESET" ] || PRESET=vox ;;
|
||||
hev) [ -n "$PRESET" ] || PRESET=hev ;;
|
||||
esac
|
||||
# The VOX preset is the Half-Life announcement voice: it implies VOX prosody
|
||||
# unless the caller explicitly disables it.
|
||||
if [ "$PRESET" = "vox" ] && [ -z "${VESKSLOP_TTS_VOX:-}" ]; then
|
||||
@@ -72,6 +107,8 @@ case "$VOICE" in
|
||||
mary) ENGVOICE="Mary" ;;
|
||||
mike) ENGVOICE="Mike" ;;
|
||||
keith-bell) ENGVOICE="Keith Bell" ;;
|
||||
vox) ENGVOICE="Keith Bell" ;;
|
||||
hev) ENGVOICE="Keith Bell" ;;
|
||||
kerry-watson) ENGVOICE="Kerry Watson" ;;
|
||||
mike-telephone) ENGVOICE="Mike (for Telephone)" ;;
|
||||
mary-telephone) ENGVOICE="Mary (for Telephone)" ;;
|
||||
@@ -350,9 +387,11 @@ 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: 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" > "$TMP/vox.txt"
|
||||
@@ -399,10 +438,19 @@ try_run_host() {
|
||||
exit 1
|
||||
}
|
||||
|
||||
# Streaming word mode writes each word as it is synthesized (see below), after the
|
||||
# filter chain exists, so the classic all-at-once path is skipped for it.
|
||||
STREAM_WORDS=0
|
||||
if [ "$STREAM" = "1" ] && [ "$WORDS" = "1" ] && [ -n "$SPEAKER_GUID" ]; then
|
||||
STREAM_WORDS=1
|
||||
fi
|
||||
|
||||
if [ "$STREAM_WORDS" != "1" ]; then
|
||||
# Word mode (Flextalk): synthesize each word and merge with silence gaps, which
|
||||
# gives the staccato radio cadence the Half-Life VOX/HEV voices are known for.
|
||||
# VOX mode takes precedence: it produces its own cadence with vendor tags.
|
||||
if [ "$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
|
||||
[ "$GAP" -gt 500 ] && GAP=500
|
||||
@@ -432,6 +480,7 @@ else
|
||||
try_run_host "$RAW" "$TAG_PREFIX$(cat "$TXT")"
|
||||
fi
|
||||
[ -s "$RAW" ] || { echo "engine produced no audio" >&2; exit 1; }
|
||||
fi
|
||||
|
||||
# Filter chain: adjustable high-pass, silence trim, fades, optional mono echo.
|
||||
case "$HIGHPASS" in *[!0-9]*|"") HIGHPASS=40 ;; esac
|
||||
@@ -441,17 +490,65 @@ case "$HIGHPASS" in *[!0-9]*|"") HIGHPASS=40 ;; esac
|
||||
case "$ECHO" in *[!0-9]*|"") ECHO=0 ;; esac
|
||||
[ "$ECHO" -gt 100 ] && ECHO=100
|
||||
|
||||
case "$ECHO_DELAY" in *[!0-9]*|"") ECHO_DELAY=60 ;; esac
|
||||
[ "$ECHO_DELAY" -lt 10 ] && ECHO_DELAY=10
|
||||
[ "$ECHO_DELAY" -gt 400 ] && ECHO_DELAY=400
|
||||
case "$ECHO_LEVEL" in *[!0-9.]*|""|".") ECHO_LEVEL=0.85 ;; esac
|
||||
ECHO_LEVEL=$(awk -v v="$ECHO_LEVEL" 'BEGIN{ if (v<0) v=0; if (v>0.95) v=0.95; printf "%.2f", v }')
|
||||
|
||||
SIL="silenceremove=start_periods=1:start_duration=0.05:start_silence=0.03:start_threshold=-50dB"
|
||||
PRE="highpass=f=$HIGHPASS,$SIL,afade=t=in:st=0:d=0.008,areverse,$SIL,afade=t=in:st=0:d=0.008,areverse"
|
||||
# aecho's in_gain/out_gain scale the dry signal as well, so a low ECHO_LEVEL used to
|
||||
# quiet the whole line (and the streaming path, which skips the loudness measurement,
|
||||
# had nothing to make it up). Keep both gains at unity and let the repeats' decay carry
|
||||
# the level; the limiter absorbs the summed peaks.
|
||||
if [ "$ECHO" -gt 0 ]; then
|
||||
DECAY=$(awk -v e="$ECHO" 'BEGIN{printf "%.2f", 0.2 + e * 0.006}')
|
||||
PRE="$PRE,aecho=0.8:0.85:60:${DECAY}"
|
||||
DECAY=$(awk -v e="$ECHO" -v l="$ECHO_LEVEL" 'BEGIN{
|
||||
d = (0.2 + e * 0.006) * (l / 0.85);
|
||||
if (d < 0.02) d = 0.02;
|
||||
if (d > 0.95) d = 0.95;
|
||||
printf "%.2f", d
|
||||
}')
|
||||
PRE="$PRE,aecho=1:1:${ECHO_DELAY}:${DECAY},alimiter=limit=0.98:level=disabled"
|
||||
fi
|
||||
|
||||
# Compression stage ("crunch"): the lossy 1990s codec character, built as its own
|
||||
# stage that runs after the rest of the chain so it colours the echo tails too. The
|
||||
# signal is quantized at a low rate / bit depth and comes back to 48 kHz so the
|
||||
# daemon's output contract holds.
|
||||
CRUNCH_FILTERS=""
|
||||
case "$CRUNCH" in
|
||||
hl90|vox90) CRUNCH_BAND="highpass=f=200,lowpass=f=5000"; CRUNCH_RATE=${CRUNCH_RATE:-11025}; CRUNCH_BITS=${CRUNCH_BITS:-8} ;;
|
||||
hl90hq) CRUNCH_BAND="highpass=f=200,lowpass=f=7000"; CRUNCH_RATE=${CRUNCH_RATE:-22050}; CRUNCH_BITS=${CRUNCH_BITS:-8} ;;
|
||||
telephone|phone) CRUNCH_BAND="highpass=f=300,lowpass=f=3400"; CRUNCH_RATE=${CRUNCH_RATE:-8000}; CRUNCH_BITS=${CRUNCH_BITS:-8} ;;
|
||||
adpcm) CRUNCH_BAND="highpass=f=200,lowpass=f=5000"; CRUNCH_RATE=${CRUNCH_RATE:-11025}; CRUNCH_BITS=${CRUNCH_BITS:-4} ;;
|
||||
crush|custom) CRUNCH_BAND="${VESKSLOP_TTS_CRUNCH_BAND:-}"; CRUNCH_RATE=${CRUNCH_RATE:-22050}; CRUNCH_BITS=${CRUNCH_BITS:-6} ;;
|
||||
off|"") ;;
|
||||
*) echo "unknown crunch preset: $CRUNCH" >&2; exit 2 ;;
|
||||
esac
|
||||
if [ "$CRUNCH" != "off" ] && [ -n "$CRUNCH" ]; then
|
||||
case "$CRUNCH_RATE" in *[!0-9]*|"") CRUNCH_RATE=22050 ;; esac
|
||||
[ "$CRUNCH_RATE" -lt 4000 ] && CRUNCH_RATE=4000
|
||||
[ "$CRUNCH_RATE" -gt 48000 ] && CRUNCH_RATE=48000
|
||||
case "$CRUNCH_BITS" in *[!0-9]*|"") CRUNCH_BITS=8 ;; esac
|
||||
[ "$CRUNCH_BITS" -lt 1 ] && CRUNCH_BITS=1
|
||||
[ "$CRUNCH_BITS" -gt 16 ] && CRUNCH_BITS=16
|
||||
[ -n "$CRUNCH_BAND" ] && CRUNCH_FILTERS="$CRUNCH_BAND,"
|
||||
CRUNCH_FILTERS="${CRUNCH_FILTERS}aresample=$CRUNCH_RATE"
|
||||
if [ "$CRUNCH_BITS" = "8" ]; then
|
||||
CRUNCH_FILTERS="$CRUNCH_FILTERS,aformat=sample_fmts=u8"
|
||||
else
|
||||
CRUNCH_FILTERS="$CRUNCH_FILTERS,acrusher=bits=$CRUNCH_BITS:mode=log:mix=1"
|
||||
fi
|
||||
CRUNCH_FILTERS="$CRUNCH_FILTERS,aresample=48000,aformat=sample_fmts=s16"
|
||||
fi
|
||||
|
||||
# Fixed-gain normalization: single-pass loudnorm misbehaves on short lines
|
||||
# (LRA=0 causes heavy attenuation), so measure EBU R128 integrated loudness and
|
||||
# true peak, then apply one gain clamped by the -3 dBFS peak target.
|
||||
M=$("$MICROSLOP_FFMPEG" -hide_banner -nostats -i "$RAW" -af "$PRE,ebur128=peak=true" \
|
||||
MEASURE_CHAIN="$PRE"
|
||||
[ -n "$CRUNCH_FILTERS" ] && MEASURE_CHAIN="$PRE,$CRUNCH_FILTERS"
|
||||
M=$("$MICROSLOP_FFMPEG" -hide_banner -nostats -i "$RAW" -af "$MEASURE_CHAIN,ebur128=peak=true" \
|
||||
-f null - 2>&1 || true)
|
||||
I=$(printf '%s' "$M" | sed -n 's/ *I: *\(-\{0,1\}[0-9.]*\) *LUFS.*/\1/p' | tail -1)
|
||||
TP=$(printf '%s' "$M" | sed -n 's/ *Peak: *\(-\{0,1\}[0-9.]*\) *dBFS.*/\1/p' | tail -1)
|
||||
@@ -468,6 +565,71 @@ else
|
||||
GAIN=0
|
||||
fi
|
||||
|
||||
# Streaming word mode: write a WAV header with unknown sizes, then append each
|
||||
# word's PCM as it is ready, so a player can start on the first word instead of
|
||||
# waiting for the whole line. The loudness measurement is skipped; set
|
||||
# VESKSLOP_TTS_STREAM_GAIN_DB if the engine levels need a nudge.
|
||||
if [ "$STREAM_WORDS" = "1" ]; then
|
||||
SGAIN=""
|
||||
case "$STREAM_GAIN" in
|
||||
''|*[!0-9.-]*|'.'|'-') ;;
|
||||
*) SGAIN=",volume=${STREAM_GAIN}dB" ;;
|
||||
esac
|
||||
|
||||
# RIFF/????/WAVE, fmt 16 bytes, PCM mono 48000 Hz s16le, data/????
|
||||
printf 'RIFF\377\377\377\377WAVEfmt \020\000\000\000\001\000\001\000\200\273\000\000\000w\001\000\002\000\020\000data\377\377\377\377' > "$OUT" \
|
||||
|| { echo "could not write $OUT" >&2; exit 1; }
|
||||
|
||||
set -f
|
||||
# shellcheck disable=SC2046
|
||||
set -- $(cat "$TXT")
|
||||
set +f
|
||||
WORD_COUNT=$#
|
||||
INDEX=0
|
||||
GAP=$WORD_GAP
|
||||
case "$GAP" in *[!0-9]*|"") GAP=120 ;; esac
|
||||
[ "$GAP" -gt 500 ] && GAP=500
|
||||
|
||||
# Leading hum, written once before the first word (same settings as the classic path).
|
||||
if [ "$HUM_MS" -gt 0 ]; then
|
||||
HUM_S=$(awk -v ms="$HUM_MS" 'BEGIN{printf "%.3f", ms/1000}')
|
||||
HUM_HZ_C=$(awk -v v="$HUM_HZ" 'BEGIN{ if (v<30) v=30; if (v>200) v=200; printf "%.1f", v }')
|
||||
HUM_DB_C=$(awk -v v="$HUM_DB" 'BEGIN{ if (v>-6) v=-6; if (v<-80) v=-80; printf "%.1f", v }')
|
||||
HUM_AMP_C=$(awk -v db="$HUM_DB_C" 'BEGIN{printf "%.6f", 10^(db/20)}')
|
||||
if "$MICROSLOP_FFMPEG" -hide_banner -loglevel error -f lavfi \
|
||||
-i "aevalsrc=exprs='$HUM_AMP_C*sin(2*PI*$HUM_HZ_C*t)':s=48000:d=$HUM_S" \
|
||||
-f s16le -ac 1 -ar 48000 "$TMP/hum.raw"; then
|
||||
cat "$TMP/hum.raw" >> "$OUT"
|
||||
fi
|
||||
fi
|
||||
|
||||
for word in "$@"; do
|
||||
INDEX=$((INDEX + 1))
|
||||
try_run_host "$TMP/sw$INDEX.wav" "${TAG_PREFIX}${word}"
|
||||
if ! "$MICROSLOP_FFMPEG" -hide_banner -loglevel error -y -i "$TMP/sw$INDEX.wav" \
|
||||
-af "$PRE$SGAIN${CRUNCH_FILTERS:+,$CRUNCH_FILTERS}" \
|
||||
-f s16le -ac 1 -ar 48000 "$TMP/sw$INDEX.raw"; then
|
||||
echo "streaming post-processing failed" >&2
|
||||
exit 1
|
||||
fi
|
||||
cat "$TMP/sw$INDEX.raw" >> "$OUT" 2>/dev/null || { echo "stream write failed" >&2; exit 1; }
|
||||
|
||||
# The player waits for this marker so it does not start on the bare header.
|
||||
if [ "$INDEX" = "1" ]; then : > "$OUT.ready"; fi
|
||||
|
||||
if [ "$GAP" -gt 0 ] && [ "$INDEX" -lt "$WORD_COUNT" ]; then
|
||||
if "$MICROSLOP_FFMPEG" -hide_banner -loglevel error -y -f lavfi -i "anullsrc=r=48000:cl=mono" \
|
||||
-t "$(awk -v g="$GAP" 'BEGIN{printf "%.3f", g/1000}')" \
|
||||
-f s16le -ac 1 -ar 48000 "$TMP/gap.raw"; then
|
||||
cat "$TMP/gap.raw" >> "$OUT"
|
||||
fi
|
||||
fi
|
||||
done
|
||||
|
||||
[ "$INDEX" -gt 0 ] || { echo "no words to stream" >&2; exit 1; }
|
||||
exit 0
|
||||
fi
|
||||
|
||||
TMPOUT="$TMP/out.wav"
|
||||
# Leading hum: a quiet low tone in the pre-speech padding, to prime Discord's
|
||||
# audio pipeline so the first syllable is not gated. Level/frequency/duration
|
||||
@@ -488,12 +650,12 @@ if [ "$HUM_MS" -gt 0 ]; then
|
||||
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]" \
|
||||
-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=${GAIN}dB,${CRUNCH_FILTERS:+$CRUNCH_FILTERS,}aresample=48000,aformat=sample_fmts=s16:channel_layouts=mono[a];[h][a]concat=n=2:v=0:a=1[out]" \
|
||||
-map "[out]" -c:a pcm_s16le "$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" \
|
||||
elif ! "$MICROSLOP_FFMPEG" -hide_banner -nostats -y -i "$RAW" -af "$PRE,volume=${GAIN}dB,${CRUNCH_FILTERS:+$CRUNCH_FILTERS,}aresample=48000,aformat=sample_fmts=s16" \
|
||||
-ar 48000 -ac 1 -c:a pcm_s16le "$TMPOUT" >/dev/null 2>"$TMP/ff"; then
|
||||
head -c 400 "$TMP/ff" >&2
|
||||
exit 1
|
||||
|
||||
Reference in New Issue
Block a user