@jambonz/schema 0.4.19 → 0.4.21

package/components/recognizer-gladiaOptions.schema.json

@@ -2,7 +2,7 @@
   "$schema": "https://json-schema.org/draft/2020-12/schema",
   "$id": "https://jambonz.org/schema/components/recognizer-gladiaOptions",
   "title": "Gladia Recognizer Options",
-  "description": "Gladia-specific STT options. Only applies when recognizer vendor is 'gladia'. See Gladia API documentation for available options.",
+  "description": "Gladia-specific STT options. Only applies when recognizer vendor is 'gladia'. Passed through into the Gladia live session request (e.g. language_config, pre_processing, realtime_processing); see the Gladia API documentation for available options.",
   "type": "object",
-  "additionalProperties": false
+  "additionalProperties": true
 }

package/components/recognizer-zoomOptions.schema.json

@@ -0,0 +1,45 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://jambonz.org/schema/components/recognizer-zoomOptions",
+  "title": "Zoom Recognizer Options",
+  "description": "Zoom Scribe (Live mode) STT options. Only applies when recognizer vendor is 'zoom'. Zoom segments turns server-side (silence-based) and returns one final transcript per speech turn; in the agent verb each one ends the user's turn: there are no interim results and no confidence scores (transcripts are reported with confidence 1.0). Supported languages: en-US, zh-CN, ja-JP, es-ES, it-IT, fr-FR, de-DE, ar-SA, ar-AE, pt-BR, pt-PT.",
+  "type": "object",
+  "properties": {
+    "apiKey": {
+      "type": "string",
+      "description": "Zoom Build platform API key (or JWT). Overrides the key configured in jambonz."
+    },
+    "turn_detection": {
+      "type": "object",
+      "description": "Tunes Zoom's server-side turn detection, which is silence-based: a turn ends after silence_duration_ms of silence, whether or not the sentence is complete. Out-of-range values make Zoom end the session, so they are bounded here.",
+      "properties": {
+        "threshold": {
+          "type": "number",
+          "minimum": 0.2,
+          "maximum": 0.9,
+          "description": "Speech detection threshold. Higher values need louder or clearer speech to start a turn."
+        },
+        "prefix_padding_ms": {
+          "type": "integer",
+          "minimum": 0,
+          "description": "Milliseconds of audio before detected speech to include in the turn."
+        },
+        "silence_duration_ms": {
+          "type": "integer",
+          "exclusiveMinimum": 200,
+          "description": "Milliseconds of silence that end a turn. Zoom's default is about 350; raise it so a mid-sentence pause does not split the turn."
+        }
+      },
+      "additionalProperties": false
+    },
+    "zoomSttUri": {
+      "type": "string",
+      "description": "Custom host to connect to instead of api.zoom.us (e.g. a proxy)."
+    },
+    "zoomSttUseTls": {
+      "type": "boolean",
+      "description": "Use TLS when connecting to a custom host. Default true."
+    }
+  },
+  "additionalProperties": false
+}

package/components/recognizer.schema.json

@@ -8,7 +8,7 @@
     "vendor": {
       "type": "string",
       "description": "The STT vendor to use. Must match a vendor configured in the jambonz platform.",
-      "examples": ["google", "aws", "microsoft", "deepgram", "ibm", "nvidia", "soniox", "xai", "modulate", "assemblyai", "speechmatics", "openai", "houndify", "gladia", "elevenlabs", "custom"]
+      "examples": ["google", "aws", "microsoft", "deepgram", "ibm", "nvidia", "soniox", "xai", "modulate", "zoom", "assemblyai", "speechmatics", "openai", "houndify", "gladia", "elevenlabs", "custom"]
     },
     "label": {
       "type": "string",
@@ -200,6 +200,7 @@
     "sonioxOptions": { "$ref": "recognizer-sonioxOptions" },
     "xaiOptions": { "$ref": "recognizer-xaiOptions" },
     "modulateOptions": { "$ref": "recognizer-modulateOptions" },
+    "zoomOptions": { "$ref": "recognizer-zoomOptions" },
     "assemblyAiOptions": { "$ref": "recognizer-assemblyAiOptions" },
     "speechmaticsOptions": { "$ref": "recognizer-speechmaticsOptions" },
     "openaiOptions": { "$ref": "recognizer-openaiOptions" },

package/components/synthesizer.schema.json

@@ -8,7 +8,7 @@
     "vendor": {
       "type": "string",
       "description": "The TTS vendor to use. Must match a vendor configured in the jambonz platform.",
-      "examples": ["google", "aws", "microsoft", "elevenlabs", "cartesia", "fishaudio", "gradium", "nineninesix", "deepgram", "deepgramflux", "ibm", "nvidia", "wellsaid", "whisper", "custom"]
+      "examples": ["google", "aws", "microsoft", "elevenlabs", "cartesia", "fishaudio", "gradium", "kugelaudio", "nineninesix", "deepgram", "deepgramflux", "ibm", "nvidia", "wellsaid", "whisper", "custom"]
     },
     "label": {
       "type": "string",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@jambonz/schema",
-  "version": "0.4.19",
+  "version": "0.4.21",
   "description": "JSON Schema definitions and validation for jambonz verb applications",
   "main": "index.js",
   "scripts": {

package/verbs/gptlive_s2s.schema.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json-schema.org/draft/2020-12/schema",
   "$id": "https://jambonz.org/schema/verbs/gptlive_s2s",
-  "minVersion": "11.1.0",
+  "minVersion": "11.0.4",
   "title": "GPT Live S2S",
   "description": "Shortcut for 'llm' with vendor automatically set to 'gptlive'. Connects the caller to OpenAI's GPT Live API (limited-access alpha, e.g. model gpt-live-1-boulder-alpha) for real-time speech-to-speech voice conversation. This is a different wire protocol from the OpenAI Realtime API used by 'openai_s2s': llmOptions takes only a session_update (there is no response_create \u2014 the model starts and drives the conversation itself), and work the model wants done arrives as a delegation. Set session_update.delegation.type to 'client' to be asked for free-form text context (answer with a delegation.context.append via llm:update), or to 'responses' to run a Responses API turn that can make function calls (answer with delegation.function_call_output.create). A 'responses' delegation carries a required nested object, delegation.responses, whose 'model' is mandatory and whose 'tools' take the flat Responses function shape. Tool support \u2014 mcpServers, handoff and hangup \u2014 requires delegation.type 'responses' with delegation.responses.model set. auth takes the OpenAI apiKey; the model is carried in the connection URL, so do not set session_update.model.",
   "type": "object",