@jambonz/sdk 0.1.32 → 0.3.0
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/dist/client/index.cjs +9 -3
- package/dist/client/index.cjs.map +1 -1
- package/dist/client/index.d.cts +4 -4
- package/dist/client/index.d.ts +4 -4
- package/dist/client/index.js +9 -3
- package/dist/client/index.js.map +1 -1
- package/dist/index.cjs +55 -99
- package/dist/index.cjs.map +1 -1
- package/dist/index.d.cts +4 -4
- package/dist/index.d.ts +4 -4
- package/dist/index.js +57 -101
- package/dist/index.js.map +1 -1
- package/dist/{rest-B_GQITxM.d.cts → rest-BvOtq44O.d.cts} +3 -3
- package/dist/{rest-DgctQy2b.d.ts → rest-DAAEUWsa.d.ts} +3 -3
- package/dist/{session-DVGHbtan.d.cts → session-DKaSRkIo.d.cts} +19 -19
- package/dist/{session-DVGHbtan.d.ts → session-DKaSRkIo.d.ts} +19 -19
- package/dist/types/index.d.cts +3 -3
- package/dist/types/index.d.ts +3 -3
- package/dist/{verb-builder-tayDQ0fe.d.ts → verb-builder-CFPD9yWI.d.cts} +4 -4
- package/dist/{verb-builder-BCjmdgUX.d.cts → verb-builder-D5XRbTtu.d.ts} +4 -4
- package/dist/{verbs-B18Kazd9.d.cts → verbs-DKy6nGIH.d.cts} +6 -6
- package/dist/{verbs-B18Kazd9.d.ts → verbs-DKy6nGIH.d.ts} +6 -6
- package/dist/webhook/index.cjs +38 -88
- package/dist/webhook/index.cjs.map +1 -1
- package/dist/webhook/index.d.cts +2 -2
- package/dist/webhook/index.d.ts +2 -2
- package/dist/webhook/index.js +40 -90
- package/dist/webhook/index.js.map +1 -1
- package/dist/websocket/index.cjs +46 -96
- package/dist/websocket/index.cjs.map +1 -1
- package/dist/websocket/index.d.cts +7 -7
- package/dist/websocket/index.d.ts +7 -7
- package/dist/websocket/index.js +48 -98
- package/dist/websocket/index.js.map +1 -1
- package/package.json +4 -4
- package/schema/callbacks/amd.schema.json +0 -50
- package/schema/callbacks/base.schema.json +0 -29
- package/schema/callbacks/call-status.schema.json +0 -22
- package/schema/callbacks/conference-status.schema.json +0 -24
- package/schema/callbacks/conference-wait.schema.json +0 -11
- package/schema/callbacks/conference.schema.json +0 -11
- package/schema/callbacks/dequeue.schema.json +0 -19
- package/schema/callbacks/dial-dtmf.schema.json +0 -18
- package/schema/callbacks/dial-hold.schema.json +0 -22
- package/schema/callbacks/dial-refer.schema.json +0 -28
- package/schema/callbacks/dial.schema.json +0 -31
- package/schema/callbacks/enqueue-wait.schema.json +0 -17
- package/schema/callbacks/enqueue.schema.json +0 -27
- package/schema/callbacks/gather-partial.schema.json +0 -54
- package/schema/callbacks/gather.schema.json +0 -60
- package/schema/callbacks/listen.schema.json +0 -21
- package/schema/callbacks/llm.schema.json +0 -30
- package/schema/callbacks/message.schema.json +0 -35
- package/schema/callbacks/pipeline-turn.schema.json +0 -109
- package/schema/callbacks/play.schema.json +0 -36
- package/schema/callbacks/session-new.schema.json +0 -143
- package/schema/callbacks/session-reconnect.schema.json +0 -9
- package/schema/callbacks/session-redirect.schema.json +0 -38
- package/schema/callbacks/sip-refer-event.schema.json +0 -20
- package/schema/callbacks/sip-refer.schema.json +0 -22
- package/schema/callbacks/sip-request.schema.json +0 -27
- package/schema/callbacks/transcribe-translation.schema.json +0 -24
- package/schema/callbacks/transcribe.schema.json +0 -46
- package/schema/callbacks/tts-streaming-event.schema.json +0 -77
- package/schema/callbacks/verb-status.schema.json +0 -57
- package/schema/components/actionHook.schema.json +0 -36
- package/schema/components/actionHookDelayAction.schema.json +0 -37
- package/schema/components/amd.schema.json +0 -68
- package/schema/components/auth.schema.json +0 -18
- package/schema/components/bidirectionalAudio.schema.json +0 -22
- package/schema/components/fillerNoise.schema.json +0 -25
- package/schema/components/llm-base.schema.json +0 -94
- package/schema/components/recognizer-assemblyAiOptions.schema.json +0 -66
- package/schema/components/recognizer-awsOptions.schema.json +0 -52
- package/schema/components/recognizer-azureOptions.schema.json +0 -32
- package/schema/components/recognizer-cobaltOptions.schema.json +0 -34
- package/schema/components/recognizer-customOptions.schema.json +0 -27
- package/schema/components/recognizer-deepgramOptions.schema.json +0 -147
- package/schema/components/recognizer-elevenlabsOptions.schema.json +0 -39
- package/schema/components/recognizer-gladiaOptions.schema.json +0 -8
- package/schema/components/recognizer-googleOptions.schema.json +0 -35
- package/schema/components/recognizer-houndifyOptions.schema.json +0 -53
- package/schema/components/recognizer-ibmOptions.schema.json +0 -54
- package/schema/components/recognizer-nuanceOptions.schema.json +0 -150
- package/schema/components/recognizer-nvidiaOptions.schema.json +0 -39
- package/schema/components/recognizer-openaiOptions.schema.json +0 -59
- package/schema/components/recognizer-sonioxOptions.schema.json +0 -46
- package/schema/components/recognizer-speechmaticsOptions.schema.json +0 -100
- package/schema/components/recognizer-verbioOptions.schema.json +0 -46
- package/schema/components/recognizer.schema.json +0 -216
- package/schema/components/synthesizer.schema.json +0 -82
- package/schema/components/target.schema.json +0 -105
- package/schema/components/vad.schema.json +0 -48
- package/schema/jambonz-app.schema.json +0 -112
- package/schema/verbs/alert.schema.json +0 -34
- package/schema/verbs/answer.schema.json +0 -22
- package/schema/verbs/conference.schema.json +0 -107
- package/schema/verbs/config.schema.json +0 -218
- package/schema/verbs/deepgram_s2s.schema.json +0 -81
- package/schema/verbs/dequeue.schema.json +0 -51
- package/schema/verbs/dial.schema.json +0 -187
- package/schema/verbs/dialogflow.schema.json +0 -148
- package/schema/verbs/dtmf.schema.json +0 -49
- package/schema/verbs/dub.schema.json +0 -103
- package/schema/verbs/elevenlabs_s2s.schema.json +0 -81
- package/schema/verbs/enqueue.schema.json +0 -53
- package/schema/verbs/gather.schema.json +0 -188
- package/schema/verbs/google_s2s.schema.json +0 -42
- package/schema/verbs/hangup.schema.json +0 -36
- package/schema/verbs/leave.schema.json +0 -22
- package/schema/verbs/listen.schema.json +0 -127
- package/schema/verbs/llm.schema.json +0 -44
- package/schema/verbs/message.schema.json +0 -82
- package/schema/verbs/openai_s2s.schema.json +0 -42
- package/schema/verbs/pause.schema.json +0 -36
- package/schema/verbs/pipeline.schema.json +0 -240
- package/schema/verbs/play.schema.json +0 -96
- package/schema/verbs/redirect.schema.json +0 -34
- package/schema/verbs/s2s.schema.json +0 -39
- package/schema/verbs/say.schema.json +0 -107
- package/schema/verbs/sip-decline.schema.json +0 -58
- package/schema/verbs/sip-refer.schema.json +0 -58
- package/schema/verbs/sip-request.schema.json +0 -54
- package/schema/verbs/stream.schema.json +0 -103
- package/schema/verbs/tag.schema.json +0 -41
- package/schema/verbs/transcribe.schema.json +0 -57
- package/schema/verbs/ultravox_s2s.schema.json +0 -41
|
@@ -1,148 +0,0 @@
|
|
|
1
|
-
{
|
|
2
|
-
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
|
3
|
-
"$id": "https://jambonz.org/schema/verbs/dialogflow",
|
|
4
|
-
"minVersion": "0.9.6",
|
|
5
|
-
"title": "Dialogflow",
|
|
6
|
-
"description": "Connects the caller to a Google Dialogflow agent for a voice conversation. Supports Dialogflow ES, CX, and CES models. The caller speaks and Dialogflow handles intent detection and response generation.",
|
|
7
|
-
"type": "object",
|
|
8
|
-
"properties": {
|
|
9
|
-
"verb": {
|
|
10
|
-
"const": "dialogflow",
|
|
11
|
-
"description": "The verb name."
|
|
12
|
-
},
|
|
13
|
-
"id": {
|
|
14
|
-
"type": "string",
|
|
15
|
-
"description": "An optional unique identifier for this verb instance."
|
|
16
|
-
},
|
|
17
|
-
"credentials": {
|
|
18
|
-
"oneOf": [
|
|
19
|
-
{
|
|
20
|
-
"type": "object",
|
|
21
|
-
"additionalProperties": true
|
|
22
|
-
},
|
|
23
|
-
{
|
|
24
|
-
"type": "string"
|
|
25
|
-
}
|
|
26
|
-
],
|
|
27
|
-
"description": "Google service account credentials as a JSON object or stringified JSON."
|
|
28
|
-
},
|
|
29
|
-
"project": {
|
|
30
|
-
"type": "string",
|
|
31
|
-
"description": "The Google Cloud project ID."
|
|
32
|
-
},
|
|
33
|
-
"agent": {
|
|
34
|
-
"type": "string",
|
|
35
|
-
"description": "The Dialogflow agent ID. Required for CX agents."
|
|
36
|
-
},
|
|
37
|
-
"environment": {
|
|
38
|
-
"type": "string",
|
|
39
|
-
"description": "The Dialogflow environment to use."
|
|
40
|
-
},
|
|
41
|
-
"region": {
|
|
42
|
-
"type": "string",
|
|
43
|
-
"description": "The Google Cloud region for the Dialogflow API endpoint."
|
|
44
|
-
},
|
|
45
|
-
"model": {
|
|
46
|
-
"type": "string",
|
|
47
|
-
"enum": [
|
|
48
|
-
"es",
|
|
49
|
-
"cx",
|
|
50
|
-
"ces"
|
|
51
|
-
],
|
|
52
|
-
"description": "The Dialogflow model type: 'es' for Dialogflow ES, 'cx' for Dialogflow CX, 'ces' for Dialogflow CES."
|
|
53
|
-
},
|
|
54
|
-
"lang": {
|
|
55
|
-
"type": "string",
|
|
56
|
-
"description": "The language code for the conversation (e.g. 'en-US')."
|
|
57
|
-
},
|
|
58
|
-
"actionHook": {
|
|
59
|
-
"$ref": "../components/actionHook",
|
|
60
|
-
"description": "A webhook invoked when the Dialogflow session ends."
|
|
61
|
-
},
|
|
62
|
-
"eventHook": {
|
|
63
|
-
"$ref": "../components/actionHook",
|
|
64
|
-
"description": "A webhook invoked for Dialogflow events during the conversation."
|
|
65
|
-
},
|
|
66
|
-
"events": {
|
|
67
|
-
"type": "array",
|
|
68
|
-
"items": {
|
|
69
|
-
"type": "string"
|
|
70
|
-
},
|
|
71
|
-
"description": "List of event types to receive via the eventHook."
|
|
72
|
-
},
|
|
73
|
-
"welcomeEvent": {
|
|
74
|
-
"type": "string",
|
|
75
|
-
"description": "A Dialogflow event to trigger at the start of the conversation (e.g. 'welcome')."
|
|
76
|
-
},
|
|
77
|
-
"welcomeEventParams": {
|
|
78
|
-
"type": "object",
|
|
79
|
-
"description": "Parameters to pass with the welcome event.",
|
|
80
|
-
"additionalProperties": true
|
|
81
|
-
},
|
|
82
|
-
"noInputTimeout": {
|
|
83
|
-
"type": "number",
|
|
84
|
-
"description": "Seconds to wait for caller input before triggering the no-input event."
|
|
85
|
-
},
|
|
86
|
-
"noInputEvent": {
|
|
87
|
-
"type": "string",
|
|
88
|
-
"description": "Dialogflow event to trigger when no input is received within the timeout."
|
|
89
|
-
},
|
|
90
|
-
"passDtmfAsTextInput": {
|
|
91
|
-
"type": "boolean",
|
|
92
|
-
"description": "If true, pass DTMF digits to Dialogflow as text input."
|
|
93
|
-
},
|
|
94
|
-
"thinkingMusic": {
|
|
95
|
-
"type": "string",
|
|
96
|
-
"description": "URL of an audio file to play while waiting for Dialogflow to respond."
|
|
97
|
-
},
|
|
98
|
-
"tts": {
|
|
99
|
-
"$ref": "../components/synthesizer",
|
|
100
|
-
"description": "TTS configuration for Dialogflow responses."
|
|
101
|
-
},
|
|
102
|
-
"bargein": {
|
|
103
|
-
"type": "boolean",
|
|
104
|
-
"description": "If true, allow the caller to interrupt Dialogflow responses with speech."
|
|
105
|
-
},
|
|
106
|
-
"queryInput": {
|
|
107
|
-
"type": "object",
|
|
108
|
-
"description": "Initial query input to send to Dialogflow.",
|
|
109
|
-
"properties": {
|
|
110
|
-
"text": {
|
|
111
|
-
"type": "string",
|
|
112
|
-
"description": "Text input."
|
|
113
|
-
},
|
|
114
|
-
"intent": {
|
|
115
|
-
"type": "string",
|
|
116
|
-
"description": "Intent to trigger."
|
|
117
|
-
},
|
|
118
|
-
"event": {
|
|
119
|
-
"type": "string",
|
|
120
|
-
"description": "Event to trigger."
|
|
121
|
-
},
|
|
122
|
-
"dtmf": {
|
|
123
|
-
"type": "string",
|
|
124
|
-
"description": "DTMF input."
|
|
125
|
-
}
|
|
126
|
-
},
|
|
127
|
-
"additionalProperties": false
|
|
128
|
-
}
|
|
129
|
-
},
|
|
130
|
-
"required": [
|
|
131
|
-
"project",
|
|
132
|
-
"credentials",
|
|
133
|
-
"lang"
|
|
134
|
-
],
|
|
135
|
-
"examples": [
|
|
136
|
-
{
|
|
137
|
-
"verb": "dialogflow",
|
|
138
|
-
"project": "my-gcp-project",
|
|
139
|
-
"credentials": "{\"type\": \"service_account\", \"project_id\": \"my-gcp-project\"}",
|
|
140
|
-
"lang": "en-US",
|
|
141
|
-
"model": "cx",
|
|
142
|
-
"agent": "my-agent-id",
|
|
143
|
-
"welcomeEvent": "welcome",
|
|
144
|
-
"actionHook": "/dialogflow-action",
|
|
145
|
-
"eventHook": "/dialogflow-event"
|
|
146
|
-
}
|
|
147
|
-
]
|
|
148
|
-
}
|
|
@@ -1,49 +0,0 @@
|
|
|
1
|
-
{
|
|
2
|
-
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
|
3
|
-
"$id": "https://jambonz.org/schema/verbs/dtmf",
|
|
4
|
-
"minVersion": "0.9.6",
|
|
5
|
-
"title": "DTMF",
|
|
6
|
-
"description": "Sends DTMF tones on the call. Used to interact with IVR systems on the far end, or to signal systems that respond to DTMF.",
|
|
7
|
-
"type": "object",
|
|
8
|
-
"properties": {
|
|
9
|
-
"verb": {
|
|
10
|
-
"const": "dtmf"
|
|
11
|
-
},
|
|
12
|
-
"id": {
|
|
13
|
-
"type": "string",
|
|
14
|
-
"description": "An optional unique identifier for this verb instance."
|
|
15
|
-
},
|
|
16
|
-
"dtmf": {
|
|
17
|
-
"type": "string",
|
|
18
|
-
"description": "The DTMF digits to send. Valid characters are 0-9, *, #, and A-D. Use 'w' for a 500ms pause between digits.",
|
|
19
|
-
"examples": [
|
|
20
|
-
"1234#",
|
|
21
|
-
"1w2w3",
|
|
22
|
-
"5551212"
|
|
23
|
-
]
|
|
24
|
-
},
|
|
25
|
-
"duration": {
|
|
26
|
-
"type": "number",
|
|
27
|
-
"description": "Duration in milliseconds for each DTMF tone.",
|
|
28
|
-
"default": 500,
|
|
29
|
-
"examples": [
|
|
30
|
-
250,
|
|
31
|
-
500
|
|
32
|
-
]
|
|
33
|
-
}
|
|
34
|
-
},
|
|
35
|
-
"required": [
|
|
36
|
-
"dtmf"
|
|
37
|
-
],
|
|
38
|
-
"examples": [
|
|
39
|
-
{
|
|
40
|
-
"verb": "dtmf",
|
|
41
|
-
"dtmf": "1234#"
|
|
42
|
-
},
|
|
43
|
-
{
|
|
44
|
-
"verb": "dtmf",
|
|
45
|
-
"dtmf": "1w2w3w4",
|
|
46
|
-
"duration": 250
|
|
47
|
-
}
|
|
48
|
-
]
|
|
49
|
-
}
|
|
@@ -1,103 +0,0 @@
|
|
|
1
|
-
{
|
|
2
|
-
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
|
3
|
-
"$id": "https://jambonz.org/schema/verbs/dub",
|
|
4
|
-
"minVersion": "0.9.6",
|
|
5
|
-
"title": "Dub",
|
|
6
|
-
"description": "Manages audio dubbing tracks on a call. Allows adding, removing, and controlling auxiliary audio tracks that are mixed into the call audio. Used for background music, coaching whispers, or injecting audio from external sources.",
|
|
7
|
-
"type": "object",
|
|
8
|
-
"properties": {
|
|
9
|
-
"verb": {
|
|
10
|
-
"const": "dub"
|
|
11
|
-
},
|
|
12
|
-
"id": {
|
|
13
|
-
"type": "string",
|
|
14
|
-
"description": "An optional unique identifier for this verb instance."
|
|
15
|
-
},
|
|
16
|
-
"action": {
|
|
17
|
-
"type": "string",
|
|
18
|
-
"description": "The dubbing action to perform.",
|
|
19
|
-
"enum": [
|
|
20
|
-
"addTrack",
|
|
21
|
-
"removeTrack",
|
|
22
|
-
"silenceTrack",
|
|
23
|
-
"playOnTrack",
|
|
24
|
-
"sayOnTrack"
|
|
25
|
-
]
|
|
26
|
-
},
|
|
27
|
-
"track": {
|
|
28
|
-
"type": "string",
|
|
29
|
-
"description": "The name of the audio track. Used to reference the track in subsequent dub actions.",
|
|
30
|
-
"examples": [
|
|
31
|
-
"background-music",
|
|
32
|
-
"coach-whisper"
|
|
33
|
-
]
|
|
34
|
-
},
|
|
35
|
-
"play": {
|
|
36
|
-
"type": "string",
|
|
37
|
-
"format": "uri",
|
|
38
|
-
"description": "URL of an audio file to play on the track. Used with 'playOnTrack' action."
|
|
39
|
-
},
|
|
40
|
-
"say": {
|
|
41
|
-
"oneOf": [
|
|
42
|
-
{
|
|
43
|
-
"type": "string"
|
|
44
|
-
},
|
|
45
|
-
{
|
|
46
|
-
"type": "object",
|
|
47
|
-
"additionalProperties": true
|
|
48
|
-
}
|
|
49
|
-
],
|
|
50
|
-
"description": "Text to synthesize and play on the track. Used with 'sayOnTrack' action. Can be a string or a say configuration object."
|
|
51
|
-
},
|
|
52
|
-
"loop": {
|
|
53
|
-
"type": "boolean",
|
|
54
|
-
"description": "If true, loop the audio on the track continuously."
|
|
55
|
-
},
|
|
56
|
-
"gain": {
|
|
57
|
-
"oneOf": [
|
|
58
|
-
{
|
|
59
|
-
"type": "number"
|
|
60
|
-
},
|
|
61
|
-
{
|
|
62
|
-
"type": "string"
|
|
63
|
-
}
|
|
64
|
-
],
|
|
65
|
-
"description": "Audio gain for the track in dB. Use negative values to reduce volume.",
|
|
66
|
-
"examples": [
|
|
67
|
-
-10,
|
|
68
|
-
0,
|
|
69
|
-
6
|
|
70
|
-
]
|
|
71
|
-
}
|
|
72
|
-
},
|
|
73
|
-
"required": [
|
|
74
|
-
"action",
|
|
75
|
-
"track"
|
|
76
|
-
],
|
|
77
|
-
"examples": [
|
|
78
|
-
{
|
|
79
|
-
"verb": "dub",
|
|
80
|
-
"action": "addTrack",
|
|
81
|
-
"track": "bgm"
|
|
82
|
-
},
|
|
83
|
-
{
|
|
84
|
-
"verb": "dub",
|
|
85
|
-
"action": "playOnTrack",
|
|
86
|
-
"track": "bgm",
|
|
87
|
-
"play": "https://example.com/music.mp3",
|
|
88
|
-
"loop": true,
|
|
89
|
-
"gain": -15
|
|
90
|
-
},
|
|
91
|
-
{
|
|
92
|
-
"verb": "dub",
|
|
93
|
-
"action": "sayOnTrack",
|
|
94
|
-
"track": "coach",
|
|
95
|
-
"say": "Ask about their budget"
|
|
96
|
-
},
|
|
97
|
-
{
|
|
98
|
-
"verb": "dub",
|
|
99
|
-
"action": "removeTrack",
|
|
100
|
-
"track": "bgm"
|
|
101
|
-
}
|
|
102
|
-
]
|
|
103
|
-
}
|
|
@@ -1,81 +0,0 @@
|
|
|
1
|
-
{
|
|
2
|
-
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
|
3
|
-
"$id": "https://jambonz.org/schema/verbs/elevenlabs_s2s",
|
|
4
|
-
"minVersion": "10.1.0",
|
|
5
|
-
"title": "ElevenLabs S2S",
|
|
6
|
-
"description": "Shortcut for 'llm' with vendor automatically set to 'elevenlabs'. Connects the caller to an ElevenLabs Conversational AI agent for real-time speech-to-speech voice conversation. Unlike other s2s vendors, ElevenLabs requires a pre-configured agent_id rather than a model and messages.",
|
|
7
|
-
"type": "object",
|
|
8
|
-
"allOf": [
|
|
9
|
-
{
|
|
10
|
-
"$ref": "../components/llm-base"
|
|
11
|
-
}
|
|
12
|
-
],
|
|
13
|
-
"properties": {
|
|
14
|
-
"verb": {
|
|
15
|
-
"const": "elevenlabs_s2s",
|
|
16
|
-
"description": "The verb name."
|
|
17
|
-
},
|
|
18
|
-
"vendor": {
|
|
19
|
-
"type": "string",
|
|
20
|
-
"const": "elevenlabs",
|
|
21
|
-
"description": "The LLM vendor (always 'elevenlabs' for this shortcut)."
|
|
22
|
-
},
|
|
23
|
-
"auth": {
|
|
24
|
-
"type": "object",
|
|
25
|
-
"description": "Authentication credentials for ElevenLabs. Requires agent_id; api_key is optional (if not provided, an unsigned URL is used).",
|
|
26
|
-
"properties": {
|
|
27
|
-
"agent_id": {
|
|
28
|
-
"type": "string",
|
|
29
|
-
"description": "The ElevenLabs Conversational AI agent ID. Required."
|
|
30
|
-
},
|
|
31
|
-
"api_key": {
|
|
32
|
-
"type": "string",
|
|
33
|
-
"description": "The ElevenLabs API key. Optional; when provided, a signed URL is used for the WebSocket connection."
|
|
34
|
-
}
|
|
35
|
-
},
|
|
36
|
-
"required": [
|
|
37
|
-
"agent_id"
|
|
38
|
-
]
|
|
39
|
-
},
|
|
40
|
-
"llmOptions": {
|
|
41
|
-
"type": "object",
|
|
42
|
-
"description": "Options for the ElevenLabs conversation session.",
|
|
43
|
-
"properties": {
|
|
44
|
-
"conversation_initiation_client_data": {
|
|
45
|
-
"type": "object",
|
|
46
|
-
"description": "Optional data sent to the agent when the conversation starts.",
|
|
47
|
-
"additionalProperties": true
|
|
48
|
-
},
|
|
49
|
-
"input_sample_rate": {
|
|
50
|
-
"type": "integer",
|
|
51
|
-
"description": "Audio input sample rate in Hz.",
|
|
52
|
-
"default": 16000
|
|
53
|
-
},
|
|
54
|
-
"output_sample_rate": {
|
|
55
|
-
"type": "integer",
|
|
56
|
-
"description": "Audio output sample rate in Hz.",
|
|
57
|
-
"default": 16000
|
|
58
|
-
}
|
|
59
|
-
},
|
|
60
|
-
"additionalProperties": true
|
|
61
|
-
}
|
|
62
|
-
},
|
|
63
|
-
"required": [
|
|
64
|
-
"auth"
|
|
65
|
-
],
|
|
66
|
-
"examples": [
|
|
67
|
-
{
|
|
68
|
-
"verb": "elevenlabs_s2s",
|
|
69
|
-
"auth": {
|
|
70
|
-
"agent_id": "your-elevenlabs-agent-id",
|
|
71
|
-
"api_key": "your-elevenlabs-api-key"
|
|
72
|
-
},
|
|
73
|
-
"llmOptions": {},
|
|
74
|
-
"actionHook": "/s2s-complete",
|
|
75
|
-
"eventHook": "/event",
|
|
76
|
-
"events": [
|
|
77
|
-
"all"
|
|
78
|
-
]
|
|
79
|
-
}
|
|
80
|
-
]
|
|
81
|
-
}
|
|
@@ -1,53 +0,0 @@
|
|
|
1
|
-
{
|
|
2
|
-
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
|
3
|
-
"$id": "https://jambonz.org/schema/verbs/enqueue",
|
|
4
|
-
"minVersion": "0.9.6",
|
|
5
|
-
"title": "Enqueue",
|
|
6
|
-
"description": "Places the caller into a named call queue. While in the queue, the caller hears content returned by the waitHook (typically hold music or position announcements). The caller remains in the queue until dequeued by another call or process.",
|
|
7
|
-
"type": "object",
|
|
8
|
-
"properties": {
|
|
9
|
-
"verb": {
|
|
10
|
-
"const": "enqueue"
|
|
11
|
-
},
|
|
12
|
-
"id": {
|
|
13
|
-
"type": "string",
|
|
14
|
-
"description": "An optional unique identifier for this verb instance."
|
|
15
|
-
},
|
|
16
|
-
"name": {
|
|
17
|
-
"type": "string",
|
|
18
|
-
"description": "The name of the queue to place the caller in. Queues are created implicitly when first referenced.",
|
|
19
|
-
"examples": [
|
|
20
|
-
"support",
|
|
21
|
-
"sales"
|
|
22
|
-
]
|
|
23
|
-
},
|
|
24
|
-
"actionHook": {
|
|
25
|
-
"$ref": "../components/actionHook",
|
|
26
|
-
"description": "A webhook invoked when the caller leaves the queue (either dequeued or hung up). Should return the next verbs to execute."
|
|
27
|
-
},
|
|
28
|
-
"waitHook": {
|
|
29
|
-
"$ref": "../components/actionHook",
|
|
30
|
-
"description": "A webhook invoked immediately when the caller enters the queue and periodically while waiting. Should return verbs to play to the caller (e.g. hold music, queue position announcements)."
|
|
31
|
-
},
|
|
32
|
-
"priority": {
|
|
33
|
-
"type": "number",
|
|
34
|
-
"description": "The priority of this caller in the queue. Lower numbers are higher priority and are dequeued first.",
|
|
35
|
-
"examples": [
|
|
36
|
-
1,
|
|
37
|
-
5,
|
|
38
|
-
10
|
|
39
|
-
]
|
|
40
|
-
}
|
|
41
|
-
},
|
|
42
|
-
"required": [
|
|
43
|
-
"name"
|
|
44
|
-
],
|
|
45
|
-
"examples": [
|
|
46
|
-
{
|
|
47
|
-
"verb": "enqueue",
|
|
48
|
-
"name": "support",
|
|
49
|
-
"waitHook": "/queue-wait",
|
|
50
|
-
"actionHook": "/queue-exit"
|
|
51
|
-
}
|
|
52
|
-
]
|
|
53
|
-
}
|
|
@@ -1,188 +0,0 @@
|
|
|
1
|
-
{
|
|
2
|
-
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
|
3
|
-
"$id": "https://jambonz.org/schema/verbs/gather",
|
|
4
|
-
"minVersion": "0.9.6",
|
|
5
|
-
"title": "Gather",
|
|
6
|
-
"description": "Collects user input via speech (STT) and/or DTMF digits. Optionally plays a prompt (using nested 'say' or 'play') while listening. When input is received, the result is sent to the actionHook which should return the next set of verbs. This is the primary verb for building interactive voice menus and conversational flows.",
|
|
7
|
-
"type": "object",
|
|
8
|
-
"properties": {
|
|
9
|
-
"verb": {
|
|
10
|
-
"const": "gather",
|
|
11
|
-
"description": "The verb name."
|
|
12
|
-
},
|
|
13
|
-
"id": {
|
|
14
|
-
"type": "string",
|
|
15
|
-
"description": "An optional unique identifier for this verb instance."
|
|
16
|
-
},
|
|
17
|
-
"actionHook": {
|
|
18
|
-
"$ref": "../components/actionHook",
|
|
19
|
-
"description": "Invoked when the gather completes. The payload includes 'reason' ('speechDetected', 'dtmfDetected', or 'timeout'), 'speech' (object with alternatives[].transcript and alternatives[].confidence when reason is speechDetected), and 'digits' (string when reason is dtmfDetected). In webhook mode this is a URL that receives an HTTP POST. In WebSocket mode this is an event name — use session.on('/hookName', (evt) => {...}) and respond with session.reply()."
|
|
20
|
-
},
|
|
21
|
-
"input": {
|
|
22
|
-
"type": "array",
|
|
23
|
-
"items": {
|
|
24
|
-
"type": "string",
|
|
25
|
-
"enum": [
|
|
26
|
-
"speech",
|
|
27
|
-
"digits"
|
|
28
|
-
]
|
|
29
|
-
},
|
|
30
|
-
"description": "The types of input to accept. Can include 'speech' (STT), 'digits' (DTMF), or both.",
|
|
31
|
-
"default": [
|
|
32
|
-
"digits"
|
|
33
|
-
],
|
|
34
|
-
"examples": [
|
|
35
|
-
[
|
|
36
|
-
"speech",
|
|
37
|
-
"digits"
|
|
38
|
-
],
|
|
39
|
-
[
|
|
40
|
-
"speech"
|
|
41
|
-
],
|
|
42
|
-
[
|
|
43
|
-
"digits"
|
|
44
|
-
]
|
|
45
|
-
]
|
|
46
|
-
},
|
|
47
|
-
"finishOnKey": {
|
|
48
|
-
"type": "string",
|
|
49
|
-
"description": "A DTMF key that signals the end of digit input. The key itself is not included in the collected digits.",
|
|
50
|
-
"examples": [
|
|
51
|
-
"#",
|
|
52
|
-
"*"
|
|
53
|
-
]
|
|
54
|
-
},
|
|
55
|
-
"numDigits": {
|
|
56
|
-
"type": "number",
|
|
57
|
-
"description": "Exact number of DTMF digits to collect. Gather completes automatically when this many digits are received."
|
|
58
|
-
},
|
|
59
|
-
"minDigits": {
|
|
60
|
-
"type": "number",
|
|
61
|
-
"description": "Minimum number of DTMF digits required."
|
|
62
|
-
},
|
|
63
|
-
"maxDigits": {
|
|
64
|
-
"type": "number",
|
|
65
|
-
"description": "Maximum number of DTMF digits to collect."
|
|
66
|
-
},
|
|
67
|
-
"interDigitTimeout": {
|
|
68
|
-
"type": "number",
|
|
69
|
-
"description": "Time in seconds to wait between DTMF digits before considering input complete.",
|
|
70
|
-
"examples": [
|
|
71
|
-
5
|
|
72
|
-
]
|
|
73
|
-
},
|
|
74
|
-
"speechTimeout": {
|
|
75
|
-
"type": "number",
|
|
76
|
-
"description": "Time in seconds of silence after speech before considering the utterance complete.",
|
|
77
|
-
"examples": [
|
|
78
|
-
2,
|
|
79
|
-
3
|
|
80
|
-
]
|
|
81
|
-
},
|
|
82
|
-
"timeout": {
|
|
83
|
-
"type": "number",
|
|
84
|
-
"description": "Overall timeout in seconds. If no input is received within this time, the gather completes with no input and the actionHook is invoked.",
|
|
85
|
-
"examples": [
|
|
86
|
-
10,
|
|
87
|
-
30
|
|
88
|
-
]
|
|
89
|
-
},
|
|
90
|
-
"partialResultHook": {
|
|
91
|
-
"$ref": "../components/actionHook",
|
|
92
|
-
"description": "A webhook to invoke with interim (partial) speech recognition results. Useful for providing real-time feedback or early processing."
|
|
93
|
-
},
|
|
94
|
-
"listenDuringPrompt": {
|
|
95
|
-
"type": "boolean",
|
|
96
|
-
"description": "If true, listen for input while the prompt is playing. If false, only start listening after the prompt finishes.",
|
|
97
|
-
"default": true
|
|
98
|
-
},
|
|
99
|
-
"dtmfBargein": {
|
|
100
|
-
"type": "boolean",
|
|
101
|
-
"description": "If true, DTMF input interrupts (barges in on) any playing prompt."
|
|
102
|
-
},
|
|
103
|
-
"bargein": {
|
|
104
|
-
"type": "boolean",
|
|
105
|
-
"description": "If true, speech input interrupts (barges in on) any playing prompt."
|
|
106
|
-
},
|
|
107
|
-
"minBargeinWordCount": {
|
|
108
|
-
"type": "number",
|
|
109
|
-
"description": "Minimum number of words that must be recognized before barge-in is triggered. Prevents brief noises from interrupting prompts.",
|
|
110
|
-
"examples": [
|
|
111
|
-
1,
|
|
112
|
-
2
|
|
113
|
-
]
|
|
114
|
-
},
|
|
115
|
-
"recognizer": {
|
|
116
|
-
"$ref": "../components/recognizer",
|
|
117
|
-
"description": "Override the session-level STT configuration for this gather."
|
|
118
|
-
},
|
|
119
|
-
"say": {
|
|
120
|
-
"$ref": "say",
|
|
121
|
-
"description": "A nested 'say' verb to use as the prompt. Played to the caller while listening for input."
|
|
122
|
-
},
|
|
123
|
-
"play": {
|
|
124
|
-
"$ref": "play",
|
|
125
|
-
"description": "A nested 'play' verb to use as the prompt. Played to the caller while listening for input."
|
|
126
|
-
},
|
|
127
|
-
"fillerNoise": {
|
|
128
|
-
"$ref": "../components/fillerNoise",
|
|
129
|
-
"description": "Filler noise configuration while waiting for the actionHook to respond."
|
|
130
|
-
},
|
|
131
|
-
"actionHookDelayAction": {
|
|
132
|
-
"$ref": "../components/actionHookDelayAction",
|
|
133
|
-
"description": "Configuration for interim actions while the actionHook is processing."
|
|
134
|
-
}
|
|
135
|
-
},
|
|
136
|
-
"examples": [
|
|
137
|
-
{
|
|
138
|
-
"verb": "gather",
|
|
139
|
-
"input": [
|
|
140
|
-
"speech",
|
|
141
|
-
"digits"
|
|
142
|
-
],
|
|
143
|
-
"actionHook": "/gather-result",
|
|
144
|
-
"timeout": 15,
|
|
145
|
-
"say": {
|
|
146
|
-
"text": "Please say or enter your account number."
|
|
147
|
-
}
|
|
148
|
-
},
|
|
149
|
-
{
|
|
150
|
-
"verb": "gather",
|
|
151
|
-
"input": [
|
|
152
|
-
"digits"
|
|
153
|
-
],
|
|
154
|
-
"actionHook": "/menu-selection",
|
|
155
|
-
"numDigits": 1,
|
|
156
|
-
"say": {
|
|
157
|
-
"text": "Press 1 for sales, 2 for support, or 3 for billing."
|
|
158
|
-
}
|
|
159
|
-
},
|
|
160
|
-
{
|
|
161
|
-
"verb": "gather",
|
|
162
|
-
"input": [
|
|
163
|
-
"speech"
|
|
164
|
-
],
|
|
165
|
-
"actionHook": "/process-speech",
|
|
166
|
-
"timeout": 20,
|
|
167
|
-
"bargein": true,
|
|
168
|
-
"recognizer": {
|
|
169
|
-
"vendor": "deepgram",
|
|
170
|
-
"language": "en-US",
|
|
171
|
-
"hints": [
|
|
172
|
-
"account",
|
|
173
|
-
"balance",
|
|
174
|
-
"transfer",
|
|
175
|
-
"payment"
|
|
176
|
-
]
|
|
177
|
-
},
|
|
178
|
-
"say": {
|
|
179
|
-
"text": "How can I help you today?"
|
|
180
|
-
},
|
|
181
|
-
"fillerNoise": {
|
|
182
|
-
"enable": true,
|
|
183
|
-
"url": "https://example.com/sounds/typing.wav",
|
|
184
|
-
"startDelaySecs": 2
|
|
185
|
-
}
|
|
186
|
-
}
|
|
187
|
-
]
|
|
188
|
-
}
|
|
@@ -1,42 +0,0 @@
|
|
|
1
|
-
{
|
|
2
|
-
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
|
3
|
-
"$id": "https://jambonz.org/schema/verbs/google_s2s",
|
|
4
|
-
"minVersion": "10.1.0",
|
|
5
|
-
"title": "Google S2S",
|
|
6
|
-
"description": "Shortcut for 'llm' with vendor automatically set to 'google'. Connects the caller to a Google model for real-time speech-to-speech voice conversation.",
|
|
7
|
-
"type": "object",
|
|
8
|
-
"allOf": [
|
|
9
|
-
{
|
|
10
|
-
"$ref": "../components/llm-base"
|
|
11
|
-
}
|
|
12
|
-
],
|
|
13
|
-
"properties": {
|
|
14
|
-
"verb": {
|
|
15
|
-
"const": "google_s2s",
|
|
16
|
-
"description": "The verb name."
|
|
17
|
-
},
|
|
18
|
-
"vendor": {
|
|
19
|
-
"type": "string",
|
|
20
|
-
"const": "google",
|
|
21
|
-
"description": "The LLM vendor (always 'google' for this shortcut)."
|
|
22
|
-
}
|
|
23
|
-
},
|
|
24
|
-
"required": [
|
|
25
|
-
"llmOptions"
|
|
26
|
-
],
|
|
27
|
-
"examples": [
|
|
28
|
-
{
|
|
29
|
-
"verb": "google_s2s",
|
|
30
|
-
"model": "gemini-2.0-flash",
|
|
31
|
-
"llmOptions": {
|
|
32
|
-
"messages": [
|
|
33
|
-
{
|
|
34
|
-
"role": "system",
|
|
35
|
-
"content": "You are a helpful voice assistant."
|
|
36
|
-
}
|
|
37
|
-
]
|
|
38
|
-
},
|
|
39
|
-
"actionHook": "/s2s-complete"
|
|
40
|
-
}
|
|
41
|
-
]
|
|
42
|
-
}
|