feat(swagger): update swagger (#2464)

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>

swagger/docs.go

@@ -22,6 +22,36 @@ const docTemplate = `{
     "host": "{{.Host}}",
     "basePath": "{{.BasePath}}",
     "paths": {
+        "/tts": {
+            "post": {
+                "consumes": [
+                    "application/json"
+                ],
+                "produces": [
+                    "audio/x-wav"
+                ],
+                "summary": "Generates audio from the input text.",
+                "parameters": [
+                    {
+                        "description": "query params",
+                        "name": "request",
+                        "in": "body",
+                        "required": true,
+                        "schema": {
+                            "$ref": "#/definitions/schema.TTSRequest"
+                        }
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "generated audio/wav file",
+                        "schema": {
+                            "type": "string"
+                        }
+                    }
+                }
+            }
+        },
         "/v1/assistants": {
             "post": {
                 "summary": "Create an assistant with a model and instructions.",
@@ -48,6 +78,12 @@ const docTemplate = `{
         },
         "/v1/audio/speech": {
             "post": {
+                "consumes": [
+                    "application/json"
+                ],
+                "produces": [
+                    "audio/x-wav"
+                ],
                 "summary": "Generates audio from the input text.",
                 "parameters": [
                     {
@@ -62,7 +98,7 @@ const docTemplate = `{
                 ],
                 "responses": {
                     "200": {
-                        "description": "Response",
+                        "description": "generated audio/wav file",
                         "schema": {
                             "type": "string"
                         }
@@ -771,18 +807,26 @@ const docTemplate = `{
             }
         },
         "schema.TTSRequest": {
+            "description": "TTS request body",
             "type": "object",
             "properties": {
                 "backend": {
                     "type": "string"
                 },
                 "input": {
+                    "description": "text input",
+                    "type": "string"
+                },
+                "language": {
+                    "description": "(optional) language to use with TTS model",
                     "type": "string"
                 },
                 "model": {
+                    "description": "model name or full path",
                     "type": "string"
                 },
                 "voice": {
+                    "description": "voice audio file or speaker id",
                     "type": "string"
                 }
             }

swagger/swagger.json

@@ -15,6 +15,36 @@
     },
     "basePath": "/",
     "paths": {
+        "/tts": {
+            "post": {
+                "consumes": [
+                    "application/json"
+                ],
+                "produces": [
+                    "audio/x-wav"
+                ],
+                "summary": "Generates audio from the input text.",
+                "parameters": [
+                    {
+                        "description": "query params",
+                        "name": "request",
+                        "in": "body",
+                        "required": true,
+                        "schema": {
+                            "$ref": "#/definitions/schema.TTSRequest"
+                        }
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "generated audio/wav file",
+                        "schema": {
+                            "type": "string"
+                        }
+                    }
+                }
+            }
+        },
         "/v1/assistants": {
             "post": {
                 "summary": "Create an assistant with a model and instructions.",
@@ -41,6 +71,12 @@
         },
         "/v1/audio/speech": {
             "post": {
+                "consumes": [
+                    "application/json"
+                ],
+                "produces": [
+                    "audio/x-wav"
+                ],
                 "summary": "Generates audio from the input text.",
                 "parameters": [
                     {
@@ -55,7 +91,7 @@
                 ],
                 "responses": {
                     "200": {
-                        "description": "Response",
+                        "description": "generated audio/wav file",
                         "schema": {
                             "type": "string"
                         }
@@ -764,18 +800,26 @@
             }
         },
         "schema.TTSRequest": {
+            "description": "TTS request body",
             "type": "object",
             "properties": {
                 "backend": {
                     "type": "string"
                 },
                 "input": {
+                    "description": "text input",
+                    "type": "string"
+                },
+                "language": {
+                    "description": "(optional) language to use with TTS model",
                     "type": "string"
                 },
                 "model": {
+                    "description": "model name or full path",
                     "type": "string"
                 },
                 "voice": {
+                    "description": "voice audio file or speaker id",
                     "type": "string"
                 }
             }

swagger/swagger.yaml

@@ -367,14 +367,21 @@ definitions:
         type: integer
     type: object
   schema.TTSRequest:
+    description: TTS request body
     properties:
       backend:
         type: string
       input:
+        description: text input
+        type: string
+      language:
+        description: (optional) language to use with TTS model
         type: string
       model:
+        description: model name or full path
         type: string
       voice:
+        description: voice audio file or speaker id
         type: string
     type: object
   schema.ToolCall:
@@ -399,6 +406,25 @@ info:
   title: LocalAI API
   version: 2.0.0
 paths:
+  /tts:
+    post:
+      consumes:
+      - application/json
+      parameters:
+      - description: query params
+        in: body
+        name: request
+        required: true
+        schema:
+          $ref: '#/definitions/schema.TTSRequest'
+      produces:
+      - audio/x-wav
+      responses:
+        "200":
+          description: generated audio/wav file
+          schema:
+            type: string
+      summary: Generates audio from the input text.
   /v1/assistants:
     post:
       parameters:
@@ -416,6 +442,8 @@ paths:
       summary: Create an assistant with a model and instructions.
   /v1/audio/speech:
     post:
+      consumes:
+      - application/json
       parameters:
       - description: query params
         in: body
@@ -423,9 +451,11 @@ paths:
         required: true
         schema:
           $ref: '#/definitions/schema.TTSRequest'
+      produces:
+      - audio/x-wav
       responses:
         "200":
-          description: Response
+          description: generated audio/wav file
           schema:
             type: string
       summary: Generates audio from the input text.