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

Add crunch presets, echo options, and streaming word mode

Browse Source
This commit is contained in:
Fisto
2026-09-21 12:31:43 +02:00
parent bbb580deea
commit c66d00ee59
11 changed files with 371 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files
microslopsam/setup/test-wrapper.sh
+17
View File
@@ -119,6 +119,23 @@ VESKSLOP_TTS_VOICE=keith-bell VESKSLOP_TTS_PRESET=vox VESKSLOP_TTS_WORDS=1 \
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")"
# Crunch keeps the output contract and changes the sound.
VESKSLOP_TTS_VOICE=keith-bell run_wrapper
cp "$WORK/out.wav" "$WORK/off.wav"
VESKSLOP_TTS_VOICE=keith-bell VESKSLOP_TTS_CRUNCH=telephone run_wrapper
check "crunch keeps 48k s16le" "pcm_s16le,48000,1" \
"$("${MICROSLOP_FFMPEG:-ffmpeg}" -hide_banner -loglevel error -i "$WORK/out.wav" -f null - 2>&1 >/dev/null; ffprobe -v error -show_entries stream=codec_name,sample_rate,channels -of csv=p=0 "$WORK/out.wav")"
check "crunch changes the audio" "1" "$([ "$(md5sum < "$WORK/off.wav")" != "$(md5sum < "$WORK/out.wav")" ] && echo 1 || echo 0)"
# Streaming word mode writes a live WAV with a gap between each pair of words.
VESKSLOP_TTS_VOICE=keith-bell VESKSLOP_TTS_WORDS=1 VESKSLOP_TTS_WORD_GAP_MS=200 \
VESKSLOP_TTS_STREAM=1 run_wrapper
check "stream header" "RIFF" "$(head -c 4 "$WORK/out.wav")"
check "stream is decodable" "0" \
"$("${MICROSLOP_FFMPEG:-ffmpeg}" -hide_banner -loglevel error -i "$WORK/out.wav" -f null - >/dev/null 2>&1; echo $?)"
check "stream has a gap per word break" "2" \
"$("${MICROSLOP_FFMPEG:-ffmpeg}" -hide_banner -i "$WORK/out.wav" -af silencedetect=noise=-45dB:d=0.15 -f null - 2>&1 | grep -c silence_start)"
# 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
+129 -4
View File
@@ -16,6 +16,14 @@
# 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_ECHO_DELAY_MS echo delay 10-400 (default 60)
# VESKSLOP_TTS_ECHO_LEVEL echo output gain 0-0.95 (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)
@@ -62,6 +70,13 @@ 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=${VESKSLOP_TTS_VOX:-0}
@@ -408,6 +423,14 @@ try_run_host() {
exit 1
}
# Streaming word mode writes each word as it is synthesized (see below), after the
# filter chain exists, so the classic all-at-once path is skipped for it.
STREAM_WORDS=0
if [ "$STREAM" = "1" ] && [ "$WORDS" = "1" ] && [ -n "$SPEAKER_GUID" ]; then
STREAM_WORDS=1
fi
if [ "$STREAM_WORDS" != "1" ]; then
# Word mode (Flextalk): synthesize each word and merge with silence gaps, which
# gives the staccato radio cadence the Half-Life VOX/HEV voices are known for.
# It combines with a preset (the profile is already written) and takes precedence
@@ -442,6 +465,7 @@ else
try_run_host "$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 "$HIGHPASS" in *[!0-9]*|"") HIGHPASS=40 ;; esac
@@ -451,17 +475,56 @@ case "$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,$SIL,afade=t=in:st=0:d=0.008,areverse"
if [ "$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}"
PRE="$PRE,aecho=0.8:${ECHO_LEVEL}:${ECHO_DELAY}:${DECAY}"
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)
@@ -478,6 +541,68 @@ 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; }
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="$TMP/out.wav"
# Leading hum: a quiet low tone in the pre-speech padding, to prime Discord's
# audio pipeline so the first syllable is not gated. Level/frequency/duration
@@ -498,12 +623,12 @@ if [ "$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