374 lines
14 KiB
Bash
Executable File
374 lines
14 KiB
Bash
Executable File
#!/bin/sh
|
|
# Veskslop TTS command-provider wrapper for MicroslopSam.
|
|
#
|
|
# Recommended Veskslop configuration:
|
|
# VESKSLOP_TTS_CMD="<repo>/setup/veskslop-tts.sh {out} {text_file}"
|
|
# VESKSLOP_TTS_VOICES="$(setup/veskslop-tts.sh --voices)"
|
|
#
|
|
# Inputs:
|
|
# $1 {out} output WAV path
|
|
# $2 {text_file} UTF-8 text file
|
|
# $3... optional: voice id, speed multiplier, pitch semitones, expression
|
|
# env VESKSLOP_TTS_VOICE, VESKSLOP_TTS_SPEED, VESKSLOP_TTS_PITCH,
|
|
# VESKSLOP_TTS_EXPRESSION
|
|
# VESKSLOP_TTS_PROFILE Flextalk profile: key=value,key=value
|
|
# keys: pitch, rate, volume, expression,
|
|
# prominences, head_size, lowering
|
|
# VESKSLOP_TTS_HIGHPASS high-pass Hz (40-400, default 40)
|
|
# VESKSLOP_TTS_ECHO mono echo amount 0-100 (default 0)
|
|
# VESKSLOP_TTS_WORDS 1 = synthesize each word, merge (Flextalk)
|
|
# VESKSLOP_TTS_WORD_GAP_MS silence between words in ms (0-500)
|
|
# VESKSLOP_TTS_VOX 1 = VOX prosody, NetTTS-style (Flextalk)
|
|
# VESKSLOP_TTS_VOX_CLEAN 1 = VOX without the \!wH1/\!wH0 stutter
|
|
#
|
|
# Output: 48 kHz mono s16le WAV, trimmed, faded, loudness-normalized.
|
|
set -eu
|
|
|
|
HERE=$(CDPATH= cd -- "$(dirname -- "$0")" && pwd)
|
|
. "$HERE/config.sh"
|
|
ROOT=$MICROSLOP_ROOT
|
|
|
|
# VESKSLOP_TTS_VOICES entries: id|Name|gender|language[|flags]
|
|
# `expression=NN` marks a Flextalk voice with an Expression profile parameter and
|
|
# its registry default. Expression is applied at voice load, so the wrapper writes
|
|
# it into the Wine registry before synthesis.
|
|
VOICES="sam|Sam|male|en,mary|Mary|female|en,mike|Mike|male|en,keith-bell|Keith Bell|male|en|expression=59+defaults=pitch:27:rate:33:prominences:17:head_size:46:lowering:40:expression:59,kerry-watson|Kerry Watson|female|en|expression=100+defaults=pitch:65:rate:32:prominences:17:head_size:45:lowering:40:expression:100,mike-telephone|Mike (for Telephone)|male|en,mary-telephone|Mary (for Telephone)|female|en,mike-hall|Mike in Hall|male|en,mike-stadium|Mike in Stadium|male|en,mike-space|Mike in Space|male|en,mary-hall|Mary in Hall|female|en,mary-stadium|Mary in Stadium|female|en,mary-space|Mary in Space|female|en"
|
|
|
|
if [ "${1:-}" = "--voices" ]; then
|
|
echo "$VOICES"
|
|
exit 0
|
|
fi
|
|
|
|
OUT=${1:?missing out path}
|
|
TEXTFILE=${2:?missing text file}
|
|
VOICE=${VESKSLOP_TTS_VOICE:-${3:-sam}}
|
|
SPEED=${VESKSLOP_TTS_SPEED:-${4:-}}
|
|
PITCH=${VESKSLOP_TTS_PITCH:-${5:-}}
|
|
EXPRESSION=${VESKSLOP_TTS_EXPRESSION:-${6:-}}
|
|
PROFILE=${VESKSLOP_TTS_PROFILE:-}
|
|
HIGHPASS=${VESKSLOP_TTS_HIGHPASS:-40}
|
|
ECHO=${VESKSLOP_TTS_ECHO:-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}
|
|
|
|
case "$VOICE" in
|
|
sam) ENGVOICE="Sam" ;;
|
|
mary) ENGVOICE="Mary" ;;
|
|
mike) ENGVOICE="Mike" ;;
|
|
keith-bell) ENGVOICE="Keith Bell" ;;
|
|
kerry-watson) ENGVOICE="Kerry Watson" ;;
|
|
mike-telephone) ENGVOICE="Mike (for Telephone)" ;;
|
|
mary-telephone) ENGVOICE="Mary (for Telephone)" ;;
|
|
mike-hall) ENGVOICE="Mike in Hall" ;;
|
|
mike-stadium) ENGVOICE="Mike in Stadium" ;;
|
|
mike-space) ENGVOICE="Mike in Space" ;;
|
|
mary-hall) ENGVOICE="Mary in Hall" ;;
|
|
mary-stadium) ENGVOICE="Mary in Stadium" ;;
|
|
mary-space) ENGVOICE="Mary in Space" ;;
|
|
*) ENGVOICE="Sam" ;;
|
|
esac
|
|
|
|
# Flextalk speakers have a registry profile; MSTTS voices do not.
|
|
case "$ENGVOICE" in
|
|
"Keith Bell") SPEAKER_GUID="{11260610-C84A-11ce-AEC4-0000C0E9CB87}"; DEF_PITCH=27; DEF_RATE=33; DEF_HEAD=46 ;;
|
|
"Kerry Watson") SPEAKER_GUID="{000031CB-3699-551F-AED0-6B4893382D57}"; DEF_PITCH=65; DEF_RATE=32; DEF_HEAD=45 ;;
|
|
*) SPEAKER_GUID=""; DEF_PITCH=100; DEF_RATE=150; DEF_HEAD=45 ;;
|
|
esac
|
|
|
|
# Engine units (measured). Speed is words/min, natural rate near 150 for every
|
|
# voice. Pitch units differ per voice: the engine's natural pitch corresponds to
|
|
# about 100 (MSTTS), 106 (Keith Bell) and 186 (Kerry Watson). Semitones scale
|
|
# that natural value by 2^(st/12) and clamp to the engine range.
|
|
case "$ENGVOICE" in
|
|
"Keith Bell") SMAX=390; PMAX=250; NAT_PITCH=106 ;;
|
|
"Kerry Watson") SMAX=390; PMAX=250; NAT_PITCH=186 ;;
|
|
*) SMAX=450; PMAX=200; NAT_PITCH=100 ;;
|
|
esac
|
|
# The daemon does not export DISPLAY; keep a private Xvfb for the engine.
|
|
start_xvfb() {
|
|
if ! [ -S "$MICROSLOP_XSOCK" ]; then
|
|
"$MICROSLOP_XVFB" "$MICROSLOP_DISPLAY" -screen 0 1024x768x24 >/dev/null 2>&1 &
|
|
sleep 1
|
|
fi
|
|
}
|
|
if [ -z "${DISPLAY:-}" ]; then
|
|
start_xvfb
|
|
export DISPLAY=$MICROSLOP_DISPLAY
|
|
fi
|
|
|
|
# NetTTS-style line controls, handled here so no caller/WebUI work is needed:
|
|
# /rate N and/or /pitch N at the start of the line.
|
|
# N is a percent (100 = normal); values <= 2.0 are multipliers (/rate 1.5 = 150%).
|
|
# They override the env speed/pitch for this line and are not spoken. A line that
|
|
# contains only commands yields 100 ms of silence, so the daemon still gets a WAV.
|
|
TMP=$(mktemp -d)
|
|
trap 'rm -rf "$TMP"' EXIT
|
|
RAW="$TMP/raw.wav"
|
|
TXT="$TMP/text.cp1252"
|
|
TEXT_IN="$TEXTFILE"
|
|
if [ -f "$TEXTFILE" ]; then
|
|
set -f
|
|
# shellcheck disable=SC2046
|
|
set -- $(cat "$TEXTFILE")
|
|
set +f
|
|
CMD_SPEED=""
|
|
CMD_PITCH=""
|
|
while [ "$#" -ge 2 ]; do
|
|
case "$1" in
|
|
/rate|/pitch)
|
|
case "$2" in
|
|
''|*[!0-9.]*) break ;;
|
|
esac
|
|
if [ "$1" = "/rate" ]; then CMD_SPEED=$2; else CMD_PITCH=$2; fi
|
|
shift 2
|
|
;;
|
|
*) break ;;
|
|
esac
|
|
done
|
|
if [ -n "$CMD_SPEED" ] || [ -n "$CMD_PITCH" ]; then
|
|
if [ -n "$CMD_SPEED" ]; then
|
|
SPEED=$(awk -v v="$CMD_SPEED" 'BEGIN{ if (v<=2.0) v*=100; if (v<0) v=0; if (v>200) v=200; printf "%.4f", v/100 }')
|
|
fi
|
|
if [ -n "$CMD_PITCH" ]; then
|
|
PITCH=$(awk -v v="$CMD_PITCH" 'BEGIN{ if (v<=2.0) v*=100; if (v<0) v=0; if (v>200) v=200; printf "%.4f", 12*log(v/100)/log(2) }')
|
|
fi
|
|
if [ -z "$*" ]; then
|
|
"$MICROSLOP_FFMPEG" -hide_banner -loglevel error -f lavfi -i anullsrc=r=48000:cl=mono \
|
|
-t 0.1 -c:a pcm_s16le -y "$OUT" >/dev/null 2>&1 \
|
|
|| { echo "could not write silence" >&2; exit 1; }
|
|
exit 0
|
|
fi
|
|
printf '%s\n' "$*" > "$TMP/input.txt"
|
|
TEXT_IN="$TMP/input.txt"
|
|
fi
|
|
fi
|
|
|
|
# Build the engine arguments from the (possibly command-overridden) speed/pitch.
|
|
SET_ARGS=""
|
|
if [ -n "$SPEED" ]; then
|
|
S=$(awk -v m="$SPEED" 'BEGIN{printf "%d", 150*m+0.5}')
|
|
[ "$S" -lt 50 ] && S=50
|
|
[ "$S" -gt "$SMAX" ] && S=$SMAX
|
|
SET_ARGS="$SET_ARGS -s $S"
|
|
fi
|
|
if [ -n "$PITCH" ]; then
|
|
P=$(awk -v st="$PITCH" -v nat="$NAT_PITCH" 'BEGIN{printf "%d", nat*exp(log(2)*st/12)+0.5}')
|
|
[ "$P" -lt 50 ] && P=50
|
|
[ "$P" -gt "$PMAX" ] && P=$PMAX
|
|
SET_ARGS="$SET_ARGS -p $P"
|
|
fi
|
|
|
|
# Apply the Flextalk profile before synthesis. Profiles are read at voice load and
|
|
# the host loads the engine per request, so the values are written every call: the
|
|
# engine defaults plus any VESKSLOP_TTS_PROFILE overrides. A missing value therefore
|
|
# restores the default.
|
|
if [ -n "$SPEAKER_GUID" ]; then
|
|
P_PITCH=$DEF_PITCH
|
|
P_RATE=$DEF_RATE
|
|
P_VOLUME=100
|
|
P_PROM=17
|
|
P_HEAD=$DEF_HEAD
|
|
P_LOWER=40
|
|
P_EXPR=""
|
|
|
|
if [ -n "$PROFILE" ]; then
|
|
OLDIFS=$IFS
|
|
IFS=','
|
|
for pair in $PROFILE; do
|
|
IFS='='
|
|
# shellcheck disable=SC2086
|
|
set -- $pair
|
|
IFS=','
|
|
case "$1" in
|
|
pitch) P_PITCH=$2 ;;
|
|
rate) P_RATE=$2 ;;
|
|
volume) P_VOLUME=$2 ;;
|
|
expression) P_EXPR=$2 ;;
|
|
prominences) P_PROM=$2 ;;
|
|
head_size|headSize) P_HEAD=$2 ;;
|
|
lowering) P_LOWER=$2 ;;
|
|
esac
|
|
done
|
|
IFS=$OLDIFS
|
|
fi
|
|
|
|
if [ -n "$EXPRESSION" ]; then P_EXPR=$EXPRESSION; fi
|
|
if [ -z "$P_EXPR" ]; then
|
|
case "$ENGVOICE" in
|
|
"Keith Bell") P_EXPR=59 ;;
|
|
*) P_EXPR=100 ;;
|
|
esac
|
|
fi
|
|
|
|
for value in "$P_PITCH" "$P_RATE" "$P_VOLUME" "$P_EXPR" "$P_PROM" "$P_HEAD" "$P_LOWER"; do
|
|
case "$value" in
|
|
*[!0-9]*|"")
|
|
echo "profile values must be numbers" >&2
|
|
exit 1
|
|
;;
|
|
esac
|
|
done
|
|
|
|
REG_KEY="HKLM\\Software\\AT&T\\Watson\\2.0\\FlexTalk\\2.0\\Speakers\\$SPEAKER_GUID"
|
|
# Use printf, not echo: dash's echo interprets \2 in the key path as an
|
|
# escape (STX), which corrupts the key and makes the import a silent no-op.
|
|
{
|
|
printf 'Windows Registry Editor Version 5.00\n\n'
|
|
printf '[%s]\n' "$REG_KEY"
|
|
printf '"Pitch"=dword:%08x\n' "$P_PITCH"
|
|
printf '"Speaking Rate"=dword:%08x\n' "$P_RATE"
|
|
printf '"Volume"=dword:%08x\n' "$P_VOLUME"
|
|
printf '"Expression"=dword:%08x\n' "$P_EXPR"
|
|
printf '"Prominences"=dword:%08x\n' "$P_PROM"
|
|
printf '"Head Size"=dword:%08x\n' "$P_HEAD"
|
|
printf '"Lowering"=dword:%08x\n' "$P_LOWER"
|
|
} > "$TMP/profile.reg"
|
|
|
|
# Guard against silent reg-import failures (a malformed key would corrupt
|
|
# only the import, and reg.exe can still return 0).
|
|
if LC_ALL=C grep -q '[[:cntrl:]]' "$TMP/profile.reg"; then
|
|
echo "generated Flextalk profile is malformed" >&2
|
|
exit 1
|
|
fi
|
|
|
|
if ! command -v "$MICROSLOP_WINE" >/dev/null 2>&1; then
|
|
echo "wine is required to set the Flextalk profile" >&2
|
|
exit 1
|
|
fi
|
|
if ! "$MICROSLOP_WINE" reg import "$TMP/profile.reg" >/dev/null 2>&1; then
|
|
echo "could not write the Flextalk profile" >&2
|
|
exit 1
|
|
fi
|
|
fi
|
|
|
|
# SAPI4 is ANSI/CP1252. VOX mode (Flextalk only) first transforms the text into
|
|
# vendor tags (\!wH1/\!wH0, \!br, \!sfNN) with setup/vox_parser.py; the parser
|
|
# works on UTF-8, so it runs before the CP1252 transliteration.
|
|
TEXT_SRC="$TEXT_IN"
|
|
if [ "$VOX" = "1" ] && [ -n "$SPEAKER_GUID" ]; 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" > "$TMP/vox.txt"
|
|
else
|
|
"$MICROSLOP_PYTHON" "$MICROSLOP_ROOT/setup/vox_parser.py" < "$TEXT_IN" > "$TMP/vox.txt"
|
|
fi
|
|
TEXT_SRC="$TMP/vox.txt"
|
|
else
|
|
echo "vox mode needs python3 and setup/vox_parser.py" >&2
|
|
exit 1
|
|
fi
|
|
fi
|
|
|
|
# transliterate UTF-8 (emoji become '?')
|
|
if command -v iconv >/dev/null 2>&1; then
|
|
iconv -f UTF-8 -t WINDOWS-1252//TRANSLIT "$TEXT_SRC" > "$TXT" 2>/dev/null \
|
|
|| cp "$TEXT_SRC" "$TXT"
|
|
else
|
|
cp "$TEXT_SRC" "$TXT"
|
|
fi
|
|
|
|
HOST="$MICROSLOP_BUILD/sapi4host-winlib.exe"
|
|
if [ ! -x "$HOST" ]; then HOST="$MICROSLOP_BUILD/sapi4host.exe"; fi
|
|
if [ ! -x "$HOST" ]; then echo "engine host not built" >&2; exit 1; fi
|
|
if ! command -v "$MICROSLOP_FFMPEG" >/dev/null 2>&1; then echo "ffmpeg not found" >&2; exit 1; fi
|
|
|
|
run_host() {
|
|
# shellcheck disable=SC2086
|
|
"$HOST" -v "$ENGVOICE" -t "$2" -o "$1" $SET_ARGS >/dev/null 2>"$TMP/err"
|
|
}
|
|
|
|
# A stale private Xvfb can break audio-destination creation; retry once.
|
|
try_run_host() {
|
|
if run_host "$1" "$2"; then return 0; fi
|
|
|
|
if [ "${DISPLAY:-}" = "$MICROSLOP_DISPLAY" ]; then
|
|
pkill -f "Xvfb $MICROSLOP_DISPLAY" 2>/dev/null || true
|
|
rm -f "$MICROSLOP_XSOCK"
|
|
start_xvfb
|
|
if run_host "$1" "$2"; then return 0; fi
|
|
fi
|
|
|
|
head -c 400 "$TMP/err" >&2
|
|
exit 1
|
|
}
|
|
|
|
# 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" ] && [ "$VOX" != "1" ]; then
|
|
GAP=$WORD_GAP
|
|
case "$GAP" in *[!0-9]*|"") GAP=120 ;; esac
|
|
[ "$GAP" -gt 500 ] && GAP=500
|
|
|
|
: > "$TMP/list.txt"
|
|
INDEX=0
|
|
for word in $(cat "$TXT"); do
|
|
INDEX=$((INDEX + 1))
|
|
try_run_host "$TMP/w$INDEX.wav" "$word"
|
|
echo "file '$TMP/w$INDEX.wav'" >> "$TMP/list.txt"
|
|
|
|
if [ "$GAP" -gt 0 ]; then
|
|
"$MICROSLOP_FFMPEG" -hide_banner -loglevel error -f lavfi -i "anullsrc=r=11025:cl=mono" \
|
|
-t "$(awk -v g="$GAP" 'BEGIN{printf "%.3f", g/1000}')" -c:a pcm_s16le -y "$TMP/sil.wav" \
|
|
>/dev/null 2>&1
|
|
echo "file '$TMP/sil.wav'" >> "$TMP/list.txt"
|
|
fi
|
|
done
|
|
|
|
[ "$INDEX" -gt 0 ] || { echo "no words to speak" >&2; exit 1; }
|
|
if ! "$MICROSLOP_FFMPEG" -hide_banner -loglevel error -f concat -safe 0 -i "$TMP/list.txt" -c copy -y "$RAW" \
|
|
>/dev/null 2>&1; then
|
|
echo "could not merge the words" >&2
|
|
exit 1
|
|
fi
|
|
else
|
|
try_run_host "$RAW" "$(cat "$TXT")"
|
|
fi
|
|
[ -s "$RAW" ] || { echo "engine produced no audio" >&2; exit 1; }
|
|
|
|
# Filter chain: adjustable high-pass, silence trim, fades, optional mono echo.
|
|
case "$HIGHPASS" in *[!0-9]*|"") HIGHPASS=40 ;; esac
|
|
[ "$HIGHPASS" -lt 40 ] && HIGHPASS=40
|
|
[ "$HIGHPASS" -gt 400 ] && HIGHPASS=400
|
|
|
|
case "$ECHO" in *[!0-9]*|"") ECHO=0 ;; esac
|
|
[ "$ECHO" -gt 100 ] && ECHO=100
|
|
|
|
SIL="silenceremove=start_periods=1:start_duration=0.05:start_silence=0.03:start_threshold=-50dB"
|
|
PRE="highpass=f=$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:${DECAY}"
|
|
fi
|
|
|
|
# Fixed-gain normalization: single-pass loudnorm misbehaves on short lines
|
|
# (LRA=0 causes heavy attenuation), so measure EBU R128 integrated loudness and
|
|
# true peak, then apply one gain clamped by the -3 dBFS peak target.
|
|
M=$("$MICROSLOP_FFMPEG" -hide_banner -nostats -i "$RAW" -af "$PRE,ebur128=peak=true" \
|
|
-f null - 2>&1 || true)
|
|
I=$(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)
|
|
if [ -n "$I" ] && [ -n "$TP" ]; then
|
|
GAIN=$(awk -v i="$I" -v tp="$TP" 'BEGIN{
|
|
g = -16 - i;
|
|
lim = -3 - tp;
|
|
if (lim < g) g = lim;
|
|
if (g > 30) g = 30;
|
|
if (g < -20) g = -20;
|
|
printf "%.2f", g
|
|
}')
|
|
else
|
|
GAIN=0
|
|
fi
|
|
|
|
TMPOUT="$TMP/out.wav"
|
|
if ! "$MICROSLOP_FFMPEG" -hide_banner -nostats -y -i "$RAW" -af "$PRE,volume=${GAIN}dB" \
|
|
-ar 48000 -ac 1 -c:a pcm_s16le "$TMPOUT" >/dev/null 2>"$TMP/ff"; then
|
|
head -c 400 "$TMP/ff" >&2
|
|
exit 1
|
|
fi
|
|
[ -s "$TMPOUT" ] || { echo "post-processing produced no audio" >&2; exit 1; }
|
|
mv -f "$TMPOUT" "$OUT"
|