1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
|
#!/bin/bash
SCRIPT=$(readlink -f "$0")
SCRIPTPATH=$(dirname "$SCRIPT")
commands=("argc" "curl" "ffplay")
for cmd in "${commands[@]}"; do
if ! command -v "$cmd" &>/dev/null; then
echo "Error: $cmd is required." >&2
exit 1
fi
done
# Check for required environment variable
if [[ -z "${LLM_API_KEY}" ]]; then
echo "The environment variable LLM_API_KEY is not set."
echo "You can use the following command: 'export \$(xargs < ${SCRIPTPATH}/../.env)'"
exit 1
fi
tts_host=${TTS_API_HOST:-"http://localhost:8000"}
stt_host=${STT_API_HOST:-"http://localhost:8001"}
_choice_voice() {
if [[ "${argc_lang}" == "fr" ]]; then
echo siwis
echo tom
echo pierre
echo jessica
fi
if [[ "${argc_lang}" == "en" ]]; then
echo alba
echo jack
echo john
echo bryce
echo ryan
echo echo
fi
}
# @cmd
# @flag -p --play Play the generated speech
# @option -l --lang![en|fr] Set the language
# @option -v --voice![`_choice_voice`] Set the voice
# @option -s --speed=1.0 Set the speed
# @option -f --filename=speech.wav Set the output filename
# @arg text! Set the text
synthesize() {
http_status_code=$(curl -s "${tts_host}/v1/audio/speech" -o "${argc_filename}" -w "%{http_code}" \
-H "Authorization: Bearer ${LLM_API_KEY}" \
-H "Content-Type: application/json" \
-d "{\"model\": \"tts-1\",\"input\": \"${argc_text}\",\"voice\": \"${argc_voice}\",\"response_format\": \"wav\",\"speed\": ${argc_speed}}")
# Check the response code for successful HTTP request
if [[ "${http_status_code}" -ne 200 ]]; then
echo "Error: Failed to fetch audio file. Received HTTP status code: $http_status_code"
exit 1
fi
if [[ $argc_play -eq 1 ]]; then
ffplay "${argc_filename}" -nodisp -nostats -hide_banner -autoexit -v quiet
fi
echo "Audio file ${argc_filename} generated successfully."
}
_choice_source() {
pactl list short sources | awk '{print $2}'
}
_choice_lang() {
echo 'af', 'am', 'ar', 'as', 'az', 'ba', 'be', 'bg', 'bn', 'bo', 'br', 'bs', 'ca', 'cs', 'cy', 'da', 'de', 'el', 'en', 'es', 'et', 'eu', 'fa', 'fi', 'fo', 'fr', 'gl', 'gu', 'ha', 'haw', 'he', 'hi', 'hr', 'ht', 'hu', 'hy', 'id', 'is', 'it', 'ja', 'jw', 'ka', 'kk', 'km', 'kn', 'ko', 'la', 'lb', 'ln', 'lo', 'lt', 'lv', 'mg', 'mi', 'mk', 'ml', 'mn', 'mr', 'ms', 'mt', 'my', 'ne', 'nl', 'nn', 'no', 'oc', 'pa', 'pl', 'ps', 'pt', 'ro', 'ru', 'sa', 'sd', 'si', 'sk', 'sl', 'sn', 'so', 'sq', 'sr', 'su', 'sv', 'sw', 'ta', 'te', 'tg', 'th', 'tk', 'tl', 'tr', 'tt', 'uk', 'ur', 'uz', 'vi', 'yi', 'yo', 'yue', 'zh' | sed 's/, /\n/g'
}
# @cmd
# @option -s --source![`_choice_source`] Set the voice
# @option -f --filename=record.wav Set the output filename
record() {
parec -d "${argc_source}" --file-format=wav "${argc_filename}"
}
# @cmd
# @option -l --lang![`_choice_lang`] Set the language
# @option -f --filename! Set the output filename
transcript() {
# Transcribe the specified file
echo "Transcribing file ${argc_filename}, be patient"
curl "${stt_host}/v1/audio/transcriptions" -H "Authorization: Bearer ${LLM_API_KEY}" \
-F "file=@${argc_filename}" \
-F "stream=true" \
-F "language=${argc_lang}"
echo
}
eval "$(argc --argc-eval "$0" "$@")"
|
