@breign/client 1.0.118 → 1.0.119

package/dist/openapi.json

@@ -1439,6 +1439,105 @@
         "tags" : [ "agent" ]
       }
     },
+    "/agents/{agentId}/speech-to-text" : {
+      "post" : {
+        "description" : "Transcribes audio using the agent's speech-to-text configuration.",
+        "operationId" : "convertAgentSpeechToText",
+        "parameters" : [ {
+          "description" : "ID of the agent",
+          "in" : "path",
+          "name" : "agentId",
+          "required" : true,
+          "schema" : {
+            "format" : "uuid",
+            "type" : "string"
+          }
+        }, {
+          "description" : "Language code for transcription (optional)",
+          "in" : "query",
+          "name" : "language",
+          "schema" : {
+            "type" : "string"
+          }
+        }, {
+          "description" : "If true, returns a mock transcription without processing the file",
+          "in" : "query",
+          "name" : "dry",
+          "schema" : {
+            "type" : "boolean"
+          }
+        }, {
+          "description" : "Speech-to-text model override (e.g. whisper-1, voxtral-mini-latest)",
+          "in" : "query",
+          "name" : "model",
+          "required" : false,
+          "schema" : {
+            "type" : "string"
+          }
+        } ],
+        "requestBody" : {
+          "content" : {
+            "audio/wav" : {
+              "schema" : {
+                "format" : "binary",
+                "type" : "string"
+              }
+            },
+            "audio/wave" : {
+              "schema" : {
+                "format" : "binary",
+                "type" : "string"
+              }
+            },
+            "audio/mpeg" : {
+              "schema" : {
+                "format" : "binary",
+                "type" : "string"
+              }
+            },
+            "audio/mp4" : {
+              "schema" : {
+                "format" : "binary",
+                "type" : "string"
+              }
+            },
+            "audio/webm" : {
+              "schema" : {
+                "format" : "binary",
+                "type" : "string"
+              }
+            }
+          },
+          "required" : true
+        },
+        "responses" : {
+          "201" : {
+            "content" : {
+              "application/json" : {
+                "schema" : {
+                  "$ref" : "#/components/schemas/STTResponse"
+                }
+              }
+            },
+            "description" : "Speech transcribed successfully"
+          },
+          "400" : {
+            "description" : "Invalid request or unsupported content type"
+          },
+          "401" : {
+            "description" : "Unauthorized"
+          },
+          "404" : {
+            "description" : "Agent not found"
+          },
+          "500" : {
+            "description" : "Server error during transcription"
+          }
+        },
+        "summary" : "Convert speech to text for an agent",
+        "tags" : [ "agent" ]
+      }
+    },
     "/agents/{agentId}/tools/{toolId}" : {
       "delete" : {
         "description" : "Removes a tool from the specified agent",
@@ -3322,6 +3421,104 @@
         "tags" : [ "app" ]
       }
     },
+    "/apps/{appId}/speech-to-text" : {
+      "post" : {
+        "description" : "Transcribes audio using the app's speech-to-text configuration, falling back to the agent configuration when the app has none.",
+        "operationId" : "convertAppSpeechToText",
+        "parameters" : [ {
+          "description" : "ID of the app",
+          "in" : "path",
+          "name" : "appId",
+          "required" : true,
+          "schema" : {
+            "type" : "string"
+          }
+        }, {
+          "description" : "Language code for transcription (optional)",
+          "in" : "query",
+          "name" : "language",
+          "schema" : {
+            "type" : "string"
+          }
+        }, {
+          "description" : "If true, returns a mock transcription without processing the file",
+          "in" : "query",
+          "name" : "dry",
+          "schema" : {
+            "type" : "boolean"
+          }
+        }, {
+          "description" : "Speech-to-text model override (e.g. whisper-1, voxtral-mini-latest)",
+          "in" : "query",
+          "name" : "model",
+          "required" : false,
+          "schema" : {
+            "type" : "string"
+          }
+        } ],
+        "requestBody" : {
+          "content" : {
+            "audio/wav" : {
+              "schema" : {
+                "format" : "binary",
+                "type" : "string"
+              }
+            },
+            "audio/wave" : {
+              "schema" : {
+                "format" : "binary",
+                "type" : "string"
+              }
+            },
+            "audio/mpeg" : {
+              "schema" : {
+                "format" : "binary",
+                "type" : "string"
+              }
+            },
+            "audio/mp4" : {
+              "schema" : {
+                "format" : "binary",
+                "type" : "string"
+              }
+            },
+            "audio/webm" : {
+              "schema" : {
+                "format" : "binary",
+                "type" : "string"
+              }
+            }
+          },
+          "required" : true
+        },
+        "responses" : {
+          "201" : {
+            "content" : {
+              "application/json" : {
+                "schema" : {
+                  "$ref" : "#/components/schemas/STTResponse"
+                }
+              }
+            },
+            "description" : "Speech transcribed successfully"
+          },
+          "400" : {
+            "description" : "Invalid request or unsupported content type"
+          },
+          "401" : {
+            "description" : "Unauthorized"
+          },
+          "404" : {
+            "description" : "App not found"
+          },
+          "500" : {
+            "description" : "Server error during transcription"
+          }
+        },
+        "summary" : "Convert speech to text for an app",
+        "tags" : [ "app" ]
+      }
+    },
     "/apps/{appId}/instances" : {
       "get" : {
         "description" : "List persisted instances for an app (excludes ephemeral instances)",
@@ -5079,6 +5276,45 @@
         "tags" : [ "engine" ]
       }
     },
+    "/organizations/{organizationId}/engines/providers/with-speech-to-text" : {
+      "get" : {
+        "description" : "Returns providers that have at least one model with the speech-to-text capability enabled.",
+        "parameters" : [ {
+          "in" : "path",
+          "name" : "organizationId",
+          "required" : true,
+          "schema" : {
+            "type" : "string"
+          }
+        } ],
+        "responses" : {
+          "200" : {
+            "content" : {
+              "application/json" : {
+                "schema" : {
+                  "items" : {
+                    "$ref" : "#/components/schemas/SpeechToTextProvider"
+                  },
+                  "type" : "array"
+                }
+              }
+            },
+            "description" : "Providers with speech-to-text models"
+          },
+          "401" : {
+            "description" : "Unauthorized"
+          },
+          "403" : {
+            "description" : "Forbidden"
+          }
+        },
+        "security" : [ {
+          "ApiKeyAuth" : [ ]
+        } ],
+        "summary" : "List organization engine providers with speech-to-text models",
+        "tags" : [ "Engines" ]
+      }
+    },
     "/engines/providers/{providerId}" : {
       "delete" : {
         "description" : "Delete a provider for an organization",
@@ -9314,7 +9550,8 @@
     },
     "/tools/speech-to-text" : {
       "post" : {
-        "description" : "Transcribes audio files to text using OpenAI's Whisper model",
+        "deprecated" : true,
+        "description" : "Transcribes audio files to text using the configured speech-to-text model (OpenAI Whisper or Mistral Voxtral).\n\n**Deprecated** — use `POST /apps/{appId}/speech-to-text` or `POST /agents/{agentId}/speech-to-text` instead.\nThis route remains available temporarily for backward compatibility.\n",
         "operationId" : "convertSpeechToText",
         "parameters" : [ {
           "description" : "Language code for transcription (optional)",
@@ -9330,6 +9567,22 @@
           "schema" : {
             "type" : "boolean"
           }
+        }, {
+          "description" : "Speech-to-text model override (e.g. whisper-1, voxtral-mini-latest)",
+          "in" : "query",
+          "name" : "model",
+          "required" : false,
+          "schema" : {
+            "type" : "string"
+          }
+        }, {
+          "description" : "Application ID used to resolve the organization AI engine API keys",
+          "in" : "query",
+          "name" : "appId",
+          "required" : true,
+          "schema" : {
+            "type" : "string"
+          }
         } ],
         "requestBody" : {
           "content" : {
@@ -9383,6 +9636,9 @@
           "401" : {
             "description" : "Unauthorized"
           },
+          "404" : {
+            "description" : "App not found"
+          },
           "500" : {
             "description" : "Server error during transcription"
           }
@@ -11540,6 +11796,22 @@
           "type" : "string"
         }
       },
+      "language" : {
+        "description" : "Language code for transcription (optional)",
+        "in" : "query",
+        "name" : "language",
+        "schema" : {
+          "type" : "string"
+        }
+      },
+      "dry" : {
+        "description" : "If true, returns a mock transcription without processing the file",
+        "in" : "query",
+        "name" : "dry",
+        "schema" : {
+          "type" : "boolean"
+        }
+      },
       "page" : {
         "description" : "Page number",
         "in" : "query",
@@ -11924,22 +12196,6 @@
           "type" : "string"
         }
       },
-      "dry" : {
-        "description" : "If true, returns a mock transcription without processing the file",
-        "in" : "query",
-        "name" : "dry",
-        "schema" : {
-          "type" : "boolean"
-        }
-      },
-      "language" : {
-        "description" : "Language code for transcription (optional)",
-        "in" : "query",
-        "name" : "language",
-        "schema" : {
-          "type" : "string"
-        }
-      },
       "skillIdPath" : {
         "description" : "Skill identifier",
         "in" : "path",
@@ -12326,6 +12582,9 @@
             } ],
             "nullable" : true
           },
+          "speechToText" : {
+            "$ref" : "#/components/schemas/SpeechToTextConfig"
+          },
           "creator" : {
             "$ref" : "#/components/schemas/Agent_creator"
           },
@@ -12668,6 +12927,9 @@
               "$ref" : "#/components/schemas/ContextualKnowledgeConversation"
             } ],
             "nullable" : true
+          },
+          "speechToText" : {
+            "$ref" : "#/components/schemas/SpeechToTextConfig"
           }
         },
         "type" : "object"
@@ -13515,6 +13777,15 @@
         "required" : [ "formData", "postURL" ],
         "type" : "object"
       },
+      "STTResponse" : {
+        "properties" : {
+          "transcription" : {
+            "type" : "string"
+          }
+        },
+        "required" : [ "transcription" ],
+        "type" : "object"
+      },
       "Chat" : {
         "properties" : {
           "id" : {
@@ -14203,6 +14474,9 @@
           "voiceModelId" : {
             "type" : "string"
           },
+          "speechToText" : {
+            "$ref" : "#/components/schemas/SpeechToTextConfig"
+          },
           "lipsync" : {
             "$ref" : "#/components/schemas/Lipsync"
           },
@@ -14224,6 +14498,19 @@
         "required" : [ "agentId", "name", "streamingEnabled" ],
         "type" : "object"
       },
+      "SpeechToTextConfig" : {
+        "additionalProperties" : false,
+        "properties" : {
+          "providerId" : {
+            "type" : "string"
+          },
+          "modelId" : {
+            "type" : "string"
+          }
+        },
+        "required" : [ "modelId", "providerId" ],
+        "type" : "object"
+      },
       "Lipsync" : {
         "additionalProperties" : true,
         "properties" : {
@@ -14296,6 +14583,9 @@
           "voiceModelId" : {
             "type" : "string"
           },
+          "speechToText" : {
+            "$ref" : "#/components/schemas/SpeechToTextConfig"
+          },
           "voice" : {
             "additionalProperties" : {
               "type" : "string"
@@ -14520,6 +14810,9 @@
           "voiceModelId" : {
             "type" : "string"
           },
+          "speechToText" : {
+            "$ref" : "#/components/schemas/SpeechToTextConfig"
+          },
           "disableFillers" : {
             "type" : "boolean"
           },
@@ -15445,6 +15738,9 @@
           "hasEmbedding" : {
             "type" : "boolean"
           },
+          "hasSpeechToText" : {
+            "type" : "boolean"
+          },
           "maxTokens" : {
             "minimum" : 1,
             "type" : "integer"
@@ -15457,6 +15753,27 @@
         "required" : [ "modelId", "name" ],
         "type" : "object"
       },
+      "SpeechToTextProvider" : {
+        "properties" : {
+          "id" : {
+            "type" : "string"
+          },
+          "name" : {
+            "type" : "string"
+          },
+          "providerType" : {
+            "type" : "string"
+          },
+          "models" : {
+            "items" : {
+              "$ref" : "#/components/schemas/SpeechToTextProvider_models_inner"
+            },
+            "type" : "array"
+          }
+        },
+        "required" : [ "id", "models", "name", "providerType" ],
+        "type" : "object"
+      },
       "ProviderSimple" : {
         "properties" : {
           "id" : {
@@ -16528,15 +16845,6 @@
         "required" : [ "id", "src" ],
         "type" : "object"
       },
-      "STTResponse" : {
-        "properties" : {
-          "transcription" : {
-            "type" : "string"
-          }
-        },
-        "required" : [ "transcription" ],
-        "type" : "object"
-      },
       "ToolSecure" : {
         "additionalProperties" : true,
         "properties" : {
@@ -18684,6 +18992,21 @@
         "required" : [ "engine", "id", "name" ],
         "type" : "object"
       },
+      "SpeechToTextProvider_models_inner" : {
+        "properties" : {
+          "id" : {
+            "type" : "string"
+          },
+          "modelId" : {
+            "type" : "string"
+          },
+          "name" : {
+            "type" : "string"
+          }
+        },
+        "required" : [ "modelId", "name" ],
+        "type" : "object"
+      },
       "MetricForAgent_identifier" : {
         "properties" : {
           "agentId" : {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@breign/client",
-  "version": "1.0.118",
+  "version": "1.0.119",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",