verbalcoding 0.2.5 → 0.2.7
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +5 -0
- package/app-node/cli_install.test.mjs +2 -1
- package/docs/i18n/CONFIGURATION.es.md +150 -0
- package/docs/i18n/CONFIGURATION.fr.md +150 -0
- package/docs/i18n/CONFIGURATION.ja.md +150 -0
- package/docs/i18n/CONFIGURATION.ko.md +49 -146
- package/docs/i18n/CONFIGURATION.ru.md +150 -0
- package/docs/i18n/CONFIGURATION.zh.md +150 -0
- package/docs/i18n/FRESH_INSTALL.es.md +124 -0
- package/docs/i18n/FRESH_INSTALL.fr.md +124 -0
- package/docs/i18n/FRESH_INSTALL.ja.md +124 -0
- package/docs/i18n/FRESH_INSTALL.ko.md +37 -114
- package/docs/i18n/FRESH_INSTALL.ru.md +124 -0
- package/docs/i18n/FRESH_INSTALL.zh.md +124 -0
- package/docs/i18n/MULTI_INSTANCE.es.md +121 -0
- package/docs/i18n/MULTI_INSTANCE.fr.md +121 -0
- package/docs/i18n/MULTI_INSTANCE.ja.md +121 -0
- package/docs/i18n/MULTI_INSTANCE.ko.md +28 -86
- package/docs/i18n/MULTI_INSTANCE.ru.md +121 -0
- package/docs/i18n/MULTI_INSTANCE.zh.md +121 -0
- package/docs/i18n/README.es.md +50 -86
- package/docs/i18n/README.fr.md +50 -86
- package/docs/i18n/README.ja.md +50 -86
- package/docs/i18n/README.ko.md +41 -113
- package/docs/i18n/README.ru.md +50 -86
- package/docs/i18n/README.zh.md +50 -86
- package/docs/i18n/RELEASE.es.md +58 -0
- package/docs/i18n/RELEASE.fr.md +58 -0
- package/docs/i18n/RELEASE.ja.md +58 -0
- package/docs/i18n/RELEASE.ko.md +36 -50
- package/docs/i18n/RELEASE.ru.md +58 -0
- package/docs/i18n/RELEASE.zh.md +58 -0
- package/docs/i18n/USAGE.es.md +134 -0
- package/docs/i18n/USAGE.fr.md +134 -0
- package/docs/i18n/USAGE.ja.md +134 -0
- package/docs/i18n/USAGE.ko.md +63 -101
- package/docs/i18n/USAGE.ru.md +134 -0
- package/docs/i18n/USAGE.zh.md +134 -0
- package/package.json +2 -2
- package/integrations/openvoice/__pycache__/synth.cpython-311.pyc +0 -0
package/docs/i18n/USAGE.ko.md
CHANGED
|
@@ -1,86 +1,71 @@
|
|
|
1
1
|
# VerbalCoding 사용 가이드
|
|
2
2
|
|
|
3
|
-
|
|
3
|
+
Operational details for 한국어 users.
|
|
4
4
|
|
|
5
|
-
## CLI
|
|
5
|
+
## CLI Commands
|
|
6
6
|
|
|
7
7
|
```bash
|
|
8
|
-
vc
|
|
9
|
-
vc
|
|
10
|
-
vc
|
|
11
|
-
vc language
|
|
12
|
-
vc
|
|
13
|
-
vc
|
|
14
|
-
vc restart auto
|
|
15
|
-
vc
|
|
16
|
-
vc
|
|
17
|
-
vc
|
|
18
|
-
vc instance
|
|
19
|
-
vc instance
|
|
20
|
-
vc
|
|
21
|
-
|
|
22
|
-
vc doctor # 비밀값을 숨긴 상태 점검 실행
|
|
23
|
-
npm run mcp # stdio MCP 서버 실행
|
|
8
|
+
vc status
|
|
9
|
+
vc language en
|
|
10
|
+
vc language ko
|
|
11
|
+
vc language auto
|
|
12
|
+
vc restart auto status
|
|
13
|
+
vc restart auto on
|
|
14
|
+
vc restart auto off
|
|
15
|
+
vc bot invite CLIENT_ID
|
|
16
|
+
vc instance status
|
|
17
|
+
vc instance setup NAME
|
|
18
|
+
vc instance start NAME
|
|
19
|
+
vc instance stop NAME
|
|
20
|
+
vc doctor
|
|
21
|
+
npm run mcp
|
|
24
22
|
```
|
|
25
23
|
|
|
26
|
-
|
|
27
|
-
|
|
28
|
-
## 실행 모드
|
|
24
|
+
Language commands update `.env`; restart with `vc start`, `./run.sh`, or your process manager.
|
|
29
25
|
|
|
30
|
-
|
|
26
|
+
## Run Modes
|
|
31
27
|
|
|
32
28
|
```bash
|
|
33
29
|
vc start
|
|
34
|
-
```
|
|
35
|
-
|
|
36
|
-
GitHub 클론에서 직접 실행:
|
|
37
|
-
|
|
38
|
-
```bash
|
|
39
30
|
./run.sh
|
|
40
|
-
```
|
|
41
|
-
|
|
42
|
-
프로젝트별 인스턴스 env로 실행:
|
|
43
|
-
|
|
44
|
-
```bash
|
|
45
31
|
./run.sh instances/my-project.env
|
|
46
|
-
# 또는
|
|
47
32
|
VERBALCODING_INSTANCE_ENV=instances/my-project.env ./run.sh
|
|
48
33
|
```
|
|
49
34
|
|
|
50
|
-
|
|
35
|
+
The bot auto-joins the first configured channel name, defaulting to `일반,General,general`.
|
|
51
36
|
|
|
52
|
-
## Discord
|
|
37
|
+
## Discord Commands
|
|
53
38
|
|
|
54
|
-
|
|
39
|
+
Before using commands, set up the Discord application/bot:
|
|
55
40
|
|
|
56
|
-
- Hermes Agent Discord
|
|
57
|
-
- Discord
|
|
41
|
+
- Hermes Agent Discord guide: <https://hermes-agent.nousresearch.com/docs/user-guide/messaging/discord>
|
|
42
|
+
- Discord official bot docs: <https://docs.discord.com/developers/bots/overview>
|
|
58
43
|
|
|
59
|
-
|
|
44
|
+
Then run `vc bot invite CLIENT_ID` for the VerbalCoding permissions.
|
|
60
45
|
|
|
61
|
-
|
|
|
46
|
+
| Command | Purpose |
|
|
62
47
|
|---|---|
|
|
63
|
-
| `!ping` |
|
|
64
|
-
| `!join` / `!leave` |
|
|
65
|
-
| `!say <text>` |
|
|
66
|
-
| `!voice-test <text>` |
|
|
67
|
-
| `!voice-clone capture` |
|
|
68
|
-
| `!voice-clone status` / `!voice-clone cancel` |
|
|
69
|
-
| `!ask <prompt>` |
|
|
70
|
-
| `!session status` |
|
|
71
|
-
| `!session new <name> <workdir> [context] --voice <voice-channel>` |
|
|
72
|
-
| `!session attach-voice [sessionName] --voice <voice-channel>` |
|
|
73
|
-
| `!session list` |
|
|
74
|
-
| `!session reset` / `!reset-session` |
|
|
75
|
-
| `!verbose on/off` |
|
|
76
|
-
| `!latency` / `!metrics` |
|
|
77
|
-
| `!sensitivity normal/conservative` |
|
|
78
|
-
|
|
79
|
-
|
|
80
|
-
|
|
81
|
-
##
|
|
82
|
-
|
|
83
|
-
`vc language ko|en|auto
|
|
48
|
+
| `!ping` | Basic bot check |
|
|
49
|
+
| `!join` / `!leave` | Join or leave voice |
|
|
50
|
+
| `!say <text>` | Speak text directly through TTS |
|
|
51
|
+
| `!voice-test <text>` | Test the active TTS backend/voice |
|
|
52
|
+
| `!voice-clone capture` | Save the next valid utterance as an OpenVoice reference sample |
|
|
53
|
+
| `!voice-clone status` / `!voice-clone cancel` | Inspect or cancel capture |
|
|
54
|
+
| `!ask <prompt>` | Send text through the same harness adapter as voice |
|
|
55
|
+
| `!session status` | Show current project/default adapter session |
|
|
56
|
+
| `!session new <name> <workdir> [context] --voice <voice-channel>` | Create a project-scoped Hermes session |
|
|
57
|
+
| `!session attach-voice [sessionName] --voice <voice-channel>` | Bind a text channel/thread to a voice channel |
|
|
58
|
+
| `!session list` | List configured project sessions |
|
|
59
|
+
| `!session reset` / `!reset-session` | Clear the current session file |
|
|
60
|
+
| `!verbose on/off` | Toggle detailed progress updates |
|
|
61
|
+
| `!latency` / `!metrics` | Show recent latency summary |
|
|
62
|
+
| `!sensitivity normal/conservative` | Switch barge-in sensitivity |
|
|
63
|
+
|
|
64
|
+
Voice equivalents such as “외부 모드”, “보수 모드”, “실내”, “기본 감도”, “상세 진행 켜”, and clear stop phrases like “잠깐”, “멈춰”, “그만” are handled by the bridge.
|
|
65
|
+
|
|
66
|
+
## Changing the Voice
|
|
67
|
+
|
|
68
|
+
`vc language ko|en|auto` changes STT language, progress language, and the matching default TTS voice together. Live voice commands can change the speaker without restart:
|
|
84
69
|
|
|
85
70
|
```text
|
|
86
71
|
남자 한국어 목소리로 바꿔
|
|
@@ -89,11 +74,9 @@ change voice to Korean female
|
|
|
89
74
|
switch speaker to English
|
|
90
75
|
```
|
|
91
76
|
|
|
92
|
-
|
|
93
|
-
|
|
94
|
-
기본 Edge 목소리 타입:
|
|
77
|
+
Built-in Edge types:
|
|
95
78
|
|
|
96
|
-
|
|
|
79
|
+
| Voice type | Edge voice |
|
|
97
80
|
|---|---|
|
|
98
81
|
| `korean_male` | `ko-KR-InJoonNeural` |
|
|
99
82
|
| `korean_female` | `ko-KR-SunHiNeural` |
|
|
@@ -101,72 +84,51 @@ switch speaker to English
|
|
|
101
84
|
| `english_male` | `en-US-GuyNeural` |
|
|
102
85
|
| `english_female` | `en-US-AriaNeural` |
|
|
103
86
|
|
|
104
|
-
|
|
87
|
+
Backend voice settings:
|
|
105
88
|
|
|
106
|
-
|
|
107
|
-
|
|
108
|
-
| 백엔드 | 목소리 설정 | 자주 쓰는 선택지 |
|
|
89
|
+
| Backend | Voice setting | Common choices |
|
|
109
90
|
|---|---|---|
|
|
110
|
-
| Edge | `TTS_VOICE_TYPE`, `TTS_VOICE` |
|
|
91
|
+
| Edge | `TTS_VOICE_TYPE`, `TTS_VOICE` | Built-in types or any Edge voice from `edge-tts --list-voices` |
|
|
111
92
|
| Supertonic | `SUPERTONIC_VOICE` | `M1`–`M5`, `F1`–`F5`; `SUPERTONIC_LANGUAGE=ko|en|es|pt|fr` |
|
|
112
|
-
| OpenVoice | `OPENVOICE_REF_AUDIO`, `OPENVOICE_STYLE` |
|
|
113
|
-
| SpeechSwift / CosyVoice | `SPEECHSWIFT_REF_AUDIO`, `SPEECHSWIFT_ENGINE`, `SPEECHSWIFT_SPEAKER` |
|
|
114
|
-
|
|
115
|
-
Supertonic과 로컬 clone 백엔드는 위 env를 바꾼 뒤 `!voice-test <text>`로 바로 들어보세요. 현재 음성 명령 기반 전환은 기본 Edge-style voice type에 매핑되어 있고, 더 풍부한 백엔드 카탈로그는 `config/tts-voices.json`에 추가할 수 있습니다.
|
|
116
|
-
|
|
117
|
-
## 긴 발화와 중간 멈춤
|
|
93
|
+
| OpenVoice | `OPENVOICE_REF_AUDIO`, `OPENVOICE_STYLE` | A permitted reference WAV plus style such as `default` |
|
|
94
|
+
| SpeechSwift / CosyVoice | `SPEECHSWIFT_REF_AUDIO`, `SPEECHSWIFT_ENGINE`, `SPEECHSWIFT_SPEAKER` | Reference WAV or backend speaker/model values |
|
|
118
95
|
|
|
119
|
-
|
|
96
|
+
## Long Dictation and Pauses
|
|
120
97
|
|
|
121
|
-
|
|
98
|
+
The default `UTTERANCE_IDLE_MS=4500` waits long enough to keep natural pauses inside one spoken instruction. Lower it for faster short commands or raise it for long dictation:
|
|
122
99
|
|
|
123
100
|
```bash
|
|
124
101
|
UTTERANCE_IDLE_MS="6000"
|
|
125
102
|
```
|
|
126
103
|
|
|
127
|
-
##
|
|
104
|
+
## Verbose Progress Mode
|
|
128
105
|
|
|
129
|
-
|
|
130
|
-
|
|
131
|
-
켜져 있으면 긴 작업 중 이런 짧은 진행 줄을 텍스트로 보냅니다.
|
|
106
|
+
Enable with `!verbose on`, `AGENT_VERBOSE_PROGRESS=1`, or “상세 진행 켜”. Progress lines look like:
|
|
132
107
|
|
|
133
108
|
```text
|
|
134
|
-
🤖
|
|
109
|
+
🤖 Hermes Agent 호출 시작
|
|
135
110
|
📖 파일 읽기 app-node/main.mjs
|
|
136
111
|
🔎 웹 검색 실행
|
|
137
112
|
⌨️ 터미널 명령 실행
|
|
138
|
-
🤖
|
|
113
|
+
🤖 Hermes Agent 응답 수신
|
|
139
114
|
```
|
|
140
115
|
|
|
141
|
-
|
|
116
|
+
Secret-looking fields are redacted and progress lines are removed from final spoken answers.
|
|
142
117
|
|
|
143
|
-
##
|
|
118
|
+
## Latency Metrics
|
|
144
119
|
|
|
145
|
-
|
|
146
|
-
|
|
147
|
-
```text
|
|
148
|
-
./.logs/latency.jsonl
|
|
149
|
-
```
|
|
150
|
-
|
|
151
|
-
각 기록에는 상태, 전체 시간, 음성 캡처 시간, 발화 idle 대기, STT 시간, 에이전트 시간, TTS 합성/재생 시간, 청크 수, 발화 길이, 답변 길이, 가능한 경우 오디오 레벨이 포함됩니다.
|
|
152
|
-
|
|
153
|
-
Discord에서:
|
|
120
|
+
Latency records are written to `./.logs/latency.jsonl`. In Discord, run:
|
|
154
121
|
|
|
155
122
|
```text
|
|
156
123
|
!latency
|
|
157
124
|
!metrics
|
|
158
125
|
```
|
|
159
126
|
|
|
160
|
-
|
|
161
|
-
|
|
162
|
-
## 테스트
|
|
127
|
+
## Testing
|
|
163
128
|
|
|
164
129
|
```bash
|
|
165
130
|
node --check app-node/main.mjs
|
|
166
131
|
npm test
|
|
167
132
|
bash -n run.sh scripts/install.sh
|
|
168
|
-
npm pack --dry-run
|
|
169
133
|
vc doctor
|
|
170
134
|
```
|
|
171
|
-
|
|
172
|
-
`vc doctor`는 비밀값을 출력하지 않고 필수 값이 설정됐는지만 확인합니다. 또한 `instances/*.env`에서 중복 토큰 지문과 충돌하는 런타임 경로를 검사합니다.
|
|
@@ -0,0 +1,134 @@
|
|
|
1
|
+
# VerbalCoding Руководство по использованию
|
|
2
|
+
|
|
3
|
+
Operational details for Русский users.
|
|
4
|
+
|
|
5
|
+
## CLI Commands
|
|
6
|
+
|
|
7
|
+
```bash
|
|
8
|
+
vc status
|
|
9
|
+
vc language en
|
|
10
|
+
vc language ko
|
|
11
|
+
vc language auto
|
|
12
|
+
vc restart auto status
|
|
13
|
+
vc restart auto on
|
|
14
|
+
vc restart auto off
|
|
15
|
+
vc bot invite CLIENT_ID
|
|
16
|
+
vc instance status
|
|
17
|
+
vc instance setup NAME
|
|
18
|
+
vc instance start NAME
|
|
19
|
+
vc instance stop NAME
|
|
20
|
+
vc doctor
|
|
21
|
+
npm run mcp
|
|
22
|
+
```
|
|
23
|
+
|
|
24
|
+
Language commands update `.env`; restart with `vc start`, `./run.sh`, or your process manager.
|
|
25
|
+
|
|
26
|
+
## Run Modes
|
|
27
|
+
|
|
28
|
+
```bash
|
|
29
|
+
vc start
|
|
30
|
+
./run.sh
|
|
31
|
+
./run.sh instances/my-project.env
|
|
32
|
+
VERBALCODING_INSTANCE_ENV=instances/my-project.env ./run.sh
|
|
33
|
+
```
|
|
34
|
+
|
|
35
|
+
The bot auto-joins the first configured channel name, defaulting to `일반,General,general`.
|
|
36
|
+
|
|
37
|
+
## Discord Commands
|
|
38
|
+
|
|
39
|
+
Before using commands, set up the Discord application/bot:
|
|
40
|
+
|
|
41
|
+
- Hermes Agent Discord guide: <https://hermes-agent.nousresearch.com/docs/user-guide/messaging/discord>
|
|
42
|
+
- Discord official bot docs: <https://docs.discord.com/developers/bots/overview>
|
|
43
|
+
|
|
44
|
+
Then run `vc bot invite CLIENT_ID` for the VerbalCoding permissions.
|
|
45
|
+
|
|
46
|
+
| Command | Purpose |
|
|
47
|
+
|---|---|
|
|
48
|
+
| `!ping` | Basic bot check |
|
|
49
|
+
| `!join` / `!leave` | Join or leave voice |
|
|
50
|
+
| `!say <text>` | Speak text directly through TTS |
|
|
51
|
+
| `!voice-test <text>` | Test the active TTS backend/voice |
|
|
52
|
+
| `!voice-clone capture` | Save the next valid utterance as an OpenVoice reference sample |
|
|
53
|
+
| `!voice-clone status` / `!voice-clone cancel` | Inspect or cancel capture |
|
|
54
|
+
| `!ask <prompt>` | Send text through the same harness adapter as voice |
|
|
55
|
+
| `!session status` | Show current project/default adapter session |
|
|
56
|
+
| `!session new <name> <workdir> [context] --voice <voice-channel>` | Create a project-scoped Hermes session |
|
|
57
|
+
| `!session attach-voice [sessionName] --voice <voice-channel>` | Bind a text channel/thread to a voice channel |
|
|
58
|
+
| `!session list` | List configured project sessions |
|
|
59
|
+
| `!session reset` / `!reset-session` | Clear the current session file |
|
|
60
|
+
| `!verbose on/off` | Toggle detailed progress updates |
|
|
61
|
+
| `!latency` / `!metrics` | Show recent latency summary |
|
|
62
|
+
| `!sensitivity normal/conservative` | Switch barge-in sensitivity |
|
|
63
|
+
|
|
64
|
+
Voice equivalents such as “외부 모드”, “보수 모드”, “실내”, “기본 감도”, “상세 진행 켜”, and clear stop phrases like “잠깐”, “멈춰”, “그만” are handled by the bridge.
|
|
65
|
+
|
|
66
|
+
## Changing the Voice
|
|
67
|
+
|
|
68
|
+
`vc language ko|en|auto` changes STT language, progress language, and the matching default TTS voice together. Live voice commands can change the speaker without restart:
|
|
69
|
+
|
|
70
|
+
```text
|
|
71
|
+
남자 한국어 목소리로 바꿔
|
|
72
|
+
여자 한국어 목소리로 바꿔
|
|
73
|
+
change voice to Korean female
|
|
74
|
+
switch speaker to English
|
|
75
|
+
```
|
|
76
|
+
|
|
77
|
+
Built-in Edge types:
|
|
78
|
+
|
|
79
|
+
| Voice type | Edge voice |
|
|
80
|
+
|---|---|
|
|
81
|
+
| `korean_male` | `ko-KR-InJoonNeural` |
|
|
82
|
+
| `korean_female` | `ko-KR-SunHiNeural` |
|
|
83
|
+
| `korean_multilingual_male` | `ko-KR-HyunsuMultilingualNeural` |
|
|
84
|
+
| `english_male` | `en-US-GuyNeural` |
|
|
85
|
+
| `english_female` | `en-US-AriaNeural` |
|
|
86
|
+
|
|
87
|
+
Backend voice settings:
|
|
88
|
+
|
|
89
|
+
| Backend | Voice setting | Common choices |
|
|
90
|
+
|---|---|---|
|
|
91
|
+
| Edge | `TTS_VOICE_TYPE`, `TTS_VOICE` | Built-in types or any Edge voice from `edge-tts --list-voices` |
|
|
92
|
+
| Supertonic | `SUPERTONIC_VOICE` | `M1`–`M5`, `F1`–`F5`; `SUPERTONIC_LANGUAGE=ko|en|es|pt|fr` |
|
|
93
|
+
| OpenVoice | `OPENVOICE_REF_AUDIO`, `OPENVOICE_STYLE` | A permitted reference WAV plus style such as `default` |
|
|
94
|
+
| SpeechSwift / CosyVoice | `SPEECHSWIFT_REF_AUDIO`, `SPEECHSWIFT_ENGINE`, `SPEECHSWIFT_SPEAKER` | Reference WAV or backend speaker/model values |
|
|
95
|
+
|
|
96
|
+
## Long Dictation and Pauses
|
|
97
|
+
|
|
98
|
+
The default `UTTERANCE_IDLE_MS=4500` waits long enough to keep natural pauses inside one spoken instruction. Lower it for faster short commands or raise it for long dictation:
|
|
99
|
+
|
|
100
|
+
```bash
|
|
101
|
+
UTTERANCE_IDLE_MS="6000"
|
|
102
|
+
```
|
|
103
|
+
|
|
104
|
+
## Verbose Progress Mode
|
|
105
|
+
|
|
106
|
+
Enable with `!verbose on`, `AGENT_VERBOSE_PROGRESS=1`, or “상세 진행 켜”. Progress lines look like:
|
|
107
|
+
|
|
108
|
+
```text
|
|
109
|
+
🤖 Hermes Agent 호출 시작
|
|
110
|
+
📖 파일 읽기 app-node/main.mjs
|
|
111
|
+
🔎 웹 검색 실행
|
|
112
|
+
⌨️ 터미널 명령 실행
|
|
113
|
+
🤖 Hermes Agent 응답 수신
|
|
114
|
+
```
|
|
115
|
+
|
|
116
|
+
Secret-looking fields are redacted and progress lines are removed from final spoken answers.
|
|
117
|
+
|
|
118
|
+
## Latency Metrics
|
|
119
|
+
|
|
120
|
+
Latency records are written to `./.logs/latency.jsonl`. In Discord, run:
|
|
121
|
+
|
|
122
|
+
```text
|
|
123
|
+
!latency
|
|
124
|
+
!metrics
|
|
125
|
+
```
|
|
126
|
+
|
|
127
|
+
## Testing
|
|
128
|
+
|
|
129
|
+
```bash
|
|
130
|
+
node --check app-node/main.mjs
|
|
131
|
+
npm test
|
|
132
|
+
bash -n run.sh scripts/install.sh
|
|
133
|
+
vc doctor
|
|
134
|
+
```
|
|
@@ -0,0 +1,134 @@
|
|
|
1
|
+
# VerbalCoding 使用指南
|
|
2
|
+
|
|
3
|
+
Operational details for 中文 users.
|
|
4
|
+
|
|
5
|
+
## CLI Commands
|
|
6
|
+
|
|
7
|
+
```bash
|
|
8
|
+
vc status
|
|
9
|
+
vc language en
|
|
10
|
+
vc language ko
|
|
11
|
+
vc language auto
|
|
12
|
+
vc restart auto status
|
|
13
|
+
vc restart auto on
|
|
14
|
+
vc restart auto off
|
|
15
|
+
vc bot invite CLIENT_ID
|
|
16
|
+
vc instance status
|
|
17
|
+
vc instance setup NAME
|
|
18
|
+
vc instance start NAME
|
|
19
|
+
vc instance stop NAME
|
|
20
|
+
vc doctor
|
|
21
|
+
npm run mcp
|
|
22
|
+
```
|
|
23
|
+
|
|
24
|
+
Language commands update `.env`; restart with `vc start`, `./run.sh`, or your process manager.
|
|
25
|
+
|
|
26
|
+
## Run Modes
|
|
27
|
+
|
|
28
|
+
```bash
|
|
29
|
+
vc start
|
|
30
|
+
./run.sh
|
|
31
|
+
./run.sh instances/my-project.env
|
|
32
|
+
VERBALCODING_INSTANCE_ENV=instances/my-project.env ./run.sh
|
|
33
|
+
```
|
|
34
|
+
|
|
35
|
+
The bot auto-joins the first configured channel name, defaulting to `일반,General,general`.
|
|
36
|
+
|
|
37
|
+
## Discord Commands
|
|
38
|
+
|
|
39
|
+
Before using commands, set up the Discord application/bot:
|
|
40
|
+
|
|
41
|
+
- Hermes Agent Discord guide: <https://hermes-agent.nousresearch.com/docs/user-guide/messaging/discord>
|
|
42
|
+
- Discord official bot docs: <https://docs.discord.com/developers/bots/overview>
|
|
43
|
+
|
|
44
|
+
Then run `vc bot invite CLIENT_ID` for the VerbalCoding permissions.
|
|
45
|
+
|
|
46
|
+
| Command | Purpose |
|
|
47
|
+
|---|---|
|
|
48
|
+
| `!ping` | Basic bot check |
|
|
49
|
+
| `!join` / `!leave` | Join or leave voice |
|
|
50
|
+
| `!say <text>` | Speak text directly through TTS |
|
|
51
|
+
| `!voice-test <text>` | Test the active TTS backend/voice |
|
|
52
|
+
| `!voice-clone capture` | Save the next valid utterance as an OpenVoice reference sample |
|
|
53
|
+
| `!voice-clone status` / `!voice-clone cancel` | Inspect or cancel capture |
|
|
54
|
+
| `!ask <prompt>` | Send text through the same harness adapter as voice |
|
|
55
|
+
| `!session status` | Show current project/default adapter session |
|
|
56
|
+
| `!session new <name> <workdir> [context] --voice <voice-channel>` | Create a project-scoped Hermes session |
|
|
57
|
+
| `!session attach-voice [sessionName] --voice <voice-channel>` | Bind a text channel/thread to a voice channel |
|
|
58
|
+
| `!session list` | List configured project sessions |
|
|
59
|
+
| `!session reset` / `!reset-session` | Clear the current session file |
|
|
60
|
+
| `!verbose on/off` | Toggle detailed progress updates |
|
|
61
|
+
| `!latency` / `!metrics` | Show recent latency summary |
|
|
62
|
+
| `!sensitivity normal/conservative` | Switch barge-in sensitivity |
|
|
63
|
+
|
|
64
|
+
Voice equivalents such as “외부 모드”, “보수 모드”, “실내”, “기본 감도”, “상세 진행 켜”, and clear stop phrases like “잠깐”, “멈춰”, “그만” are handled by the bridge.
|
|
65
|
+
|
|
66
|
+
## Changing the Voice
|
|
67
|
+
|
|
68
|
+
`vc language ko|en|auto` changes STT language, progress language, and the matching default TTS voice together. Live voice commands can change the speaker without restart:
|
|
69
|
+
|
|
70
|
+
```text
|
|
71
|
+
남자 한국어 목소리로 바꿔
|
|
72
|
+
여자 한국어 목소리로 바꿔
|
|
73
|
+
change voice to Korean female
|
|
74
|
+
switch speaker to English
|
|
75
|
+
```
|
|
76
|
+
|
|
77
|
+
Built-in Edge types:
|
|
78
|
+
|
|
79
|
+
| Voice type | Edge voice |
|
|
80
|
+
|---|---|
|
|
81
|
+
| `korean_male` | `ko-KR-InJoonNeural` |
|
|
82
|
+
| `korean_female` | `ko-KR-SunHiNeural` |
|
|
83
|
+
| `korean_multilingual_male` | `ko-KR-HyunsuMultilingualNeural` |
|
|
84
|
+
| `english_male` | `en-US-GuyNeural` |
|
|
85
|
+
| `english_female` | `en-US-AriaNeural` |
|
|
86
|
+
|
|
87
|
+
Backend voice settings:
|
|
88
|
+
|
|
89
|
+
| Backend | Voice setting | Common choices |
|
|
90
|
+
|---|---|---|
|
|
91
|
+
| Edge | `TTS_VOICE_TYPE`, `TTS_VOICE` | Built-in types or any Edge voice from `edge-tts --list-voices` |
|
|
92
|
+
| Supertonic | `SUPERTONIC_VOICE` | `M1`–`M5`, `F1`–`F5`; `SUPERTONIC_LANGUAGE=ko|en|es|pt|fr` |
|
|
93
|
+
| OpenVoice | `OPENVOICE_REF_AUDIO`, `OPENVOICE_STYLE` | A permitted reference WAV plus style such as `default` |
|
|
94
|
+
| SpeechSwift / CosyVoice | `SPEECHSWIFT_REF_AUDIO`, `SPEECHSWIFT_ENGINE`, `SPEECHSWIFT_SPEAKER` | Reference WAV or backend speaker/model values |
|
|
95
|
+
|
|
96
|
+
## Long Dictation and Pauses
|
|
97
|
+
|
|
98
|
+
The default `UTTERANCE_IDLE_MS=4500` waits long enough to keep natural pauses inside one spoken instruction. Lower it for faster short commands or raise it for long dictation:
|
|
99
|
+
|
|
100
|
+
```bash
|
|
101
|
+
UTTERANCE_IDLE_MS="6000"
|
|
102
|
+
```
|
|
103
|
+
|
|
104
|
+
## Verbose Progress Mode
|
|
105
|
+
|
|
106
|
+
Enable with `!verbose on`, `AGENT_VERBOSE_PROGRESS=1`, or “상세 진행 켜”. Progress lines look like:
|
|
107
|
+
|
|
108
|
+
```text
|
|
109
|
+
🤖 Hermes Agent 호출 시작
|
|
110
|
+
📖 파일 읽기 app-node/main.mjs
|
|
111
|
+
🔎 웹 검색 실행
|
|
112
|
+
⌨️ 터미널 명령 실행
|
|
113
|
+
🤖 Hermes Agent 응답 수신
|
|
114
|
+
```
|
|
115
|
+
|
|
116
|
+
Secret-looking fields are redacted and progress lines are removed from final spoken answers.
|
|
117
|
+
|
|
118
|
+
## Latency Metrics
|
|
119
|
+
|
|
120
|
+
Latency records are written to `./.logs/latency.jsonl`. In Discord, run:
|
|
121
|
+
|
|
122
|
+
```text
|
|
123
|
+
!latency
|
|
124
|
+
!metrics
|
|
125
|
+
```
|
|
126
|
+
|
|
127
|
+
## Testing
|
|
128
|
+
|
|
129
|
+
```bash
|
|
130
|
+
node --check app-node/main.mjs
|
|
131
|
+
npm test
|
|
132
|
+
bash -n run.sh scripts/install.sh
|
|
133
|
+
vc doctor
|
|
134
|
+
```
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "verbalcoding",
|
|
3
|
-
"version": "0.2.
|
|
3
|
+
"version": "0.2.7",
|
|
4
4
|
"description": "Discord voice bridge for CLI coding agents.",
|
|
5
5
|
"license": "MIT",
|
|
6
6
|
"repository": {
|
|
@@ -34,7 +34,7 @@
|
|
|
34
34
|
"docs/",
|
|
35
35
|
"scripts/*.mjs",
|
|
36
36
|
"scripts/*.sh",
|
|
37
|
-
"integrations/openvoice
|
|
37
|
+
"integrations/openvoice/*.py",
|
|
38
38
|
"run.sh",
|
|
39
39
|
".env.example",
|
|
40
40
|
"README.md",
|
|
Binary file
|