intentkit 0.6.13.dev2__py3-none-any.whl → 0.8.17__py3-none-any.whl

intentkit/skills/venice_audio/schema.json

@@ -1,152 +1,151 @@
-{
-    "$schema": "http://json-schema.org/draft-07/schema#",
-    "title": "Venice Audio Skills",
-    "x-icon": "https://ai.service.crestal.dev/skills/venice_audio/venice_audio.jpg",
-    "description": "Configuration for the Venice Audio skill.",
-    "type": "object",
-    "x-tags": [
-        "AI",
-        "Audio",
-        "Text to Speech"
-    ],
-    "properties": {
-        "enabled": {
-            "type": "boolean",
-            "title": "Enabled",
-            "description": "Enable or disable the Venice Audio skill.",
-            "default": false
-        },
-        "voice_model": {
-            "type": "string",
-            "title": "Voice Model",
-            "x-link": "[Listen Voice Example](https://huggingface.co/spaces/hexgrad/Kokoro-TTS)",
-            "enum": [
-                "af_heart",
-                "bm_lewis",
-                "custom"
-            ],
-            "x-enum-title": [
-                "af_heart (default female)",
-                "bm_lewis (default male)",
-                "Custom"
-            ],
-            "description": "Text to speech tool",
-            "default": "af_heart"
-        },
-        "states": {
-            "type": "object",
-            "title": "Skill States",
-            "description": "Enable/disable specific voice models. Only enable one if you want a consistent characteristic for your agent. See docs for voice details and quality grades.",
-            "properties": {
-                "text_to_speech": {
-                    "type": "string",
-                    "title": "Text to Speech",
-                    "enum": [
-                        "disabled",
-                        "public",
-                        "private"
-                    ],
-                    "x-enum-title": [
-                        "Disabled",
-                        "Agent Owner + All Users",
-                        "Agent Owner Only"
-                    ],
-                    "description": "Text to speech tool",
-                    "default": "disabled"
-                }
-            }
-        },
-        "api_key_provider": {
-            "type": "string",
-            "title": "API Key Provider",
-            "description": "Provider of the API key",
-            "enum": [
-                "agent_owner"
-            ],
-            "x-enum-title": [
-                "Owner Provided"
-            ],
-            "default": "agent_owner"
-        }
-    },
-    "required": [
-        "states",
-        "enabled"
-    ],
-    "allOf": [
-        {
-            "if": {
-                "properties": {
-                    "voice_model": {
-                        "const": "custom"
-                    }
-                }
-            },
-            "then": {
-                "properties": {
-                    "voice_model_custom": {
-                        "type": "array",
-                        "items": {
-                            "type": "string"
-                        },
-                        "title": "Voice Model (Custom)",
-                        "x-link": "[Supported Voice Model](https://docs.venice.ai/api-reference/endpoint/audio/speech#body-voice)",
-                        "description": "You can add one or more custom voice models.",
-                        "default": [
-                            "af_heart",
-                            "bm_lewis"
-                        ]
-                    }
-                },
-                "required": [
-                    "voice_model_custom"
-                ]
-            }
-        },
-        {
-            "if": {
-                "allOf": [
-                    {
-                        "properties": {
-                            "enabled": {
-                                "const": true
-                            }
-                        }
-                    },
-                    {
-                        "properties": {
-                            "api_key_provider": {
-                                "const": "agent_owner"
-                            }
-                        }
-                    }
-                ]
-            },
-            "then": {
-                "properties": {
-                    "api_key": {
-                        "type": "string",
-                        "title": "Venice API Key",
-                        "x-link": "[Get your API key](https://venice.ai/)",
-                        "x-sensitive": true,
-                        "description": "API Key for authenticating with the Venice AI API."
-                    },
-                    "rate_limit_number": {
-                        "type": "integer",
-                        "title": "Rate Limit Number",
-                        "description": "Number of requests allowed per time window."
-                    },
-                    "rate_limit_minutes": {
-                        "type": "integer",
-                        "title": "Rate Limit Minutes",
-                        "description": "Time window in minutes for rate limiting."
-                    }
-                },
-                "required": [
-                    "api_key"
-                ]
-            }
-        }
-    ],
-    "additionalProperties": true
-}
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "title": "Venice Audio Skills",
+  "x-icon": "https://ai.service.crestal.dev/skills/venice_audio/venice_audio.jpg",
+  "description": "Configuration for the Venice Audio skill.",
+  "type": "object",
+  "x-tags": [
+    "AI",
+    "Audio"
+  ],
+  "properties": {
+    "enabled": {
+      "type": "boolean",
+      "title": "Enabled",
+      "description": "Enable or disable the Venice Audio skill.",
+      "default": false
+    },
+    "voice_model": {
+      "type": "string",
+      "title": "Voice Model",
+      "x-link": "[Listen Voice Example](https://huggingface.co/spaces/hexgrad/Kokoro-TTS)",
+      "enum": [
+        "af_heart",
+        "bm_lewis",
+        "custom"
+      ],
+      "x-enum-title": [
+        "af_heart (default female)",
+        "bm_lewis (default male)",
+        "Custom"
+      ],
+      "description": "Text to speech tool",
+      "default": "af_heart"
+    },
+    "states": {
+      "type": "object",
+      "title": "Skill States",
+      "description": "Enable/disable specific voice models. Only enable one if you want a consistent characteristic for your agent. See docs for voice details and quality grades.",
+      "properties": {
+        "text_to_speech": {
+          "type": "string",
+          "title": "Text to Speech",
+          "enum": [
+            "disabled",
+            "public",
+            "private"
+          ],
+          "x-enum-title": [
+            "Disabled",
+            "Agent Owner + All Users",
+            "Agent Owner Only"
+          ],
+          "description": "Text to speech tool",
+          "default": "disabled"
+        }
+      }
+    },
+    "api_key_provider": {
+      "type": "string",
+      "title": "API Key Provider",
+      "description": "Provider of the API key",
+      "enum": [
+        "agent_owner"
+      ],
+      "x-enum-title": [
+        "Owner Provided"
+      ],
+      "default": "agent_owner"
+    }
+  },
+  "required": [
+    "states",
+    "enabled"
+  ],
+  "allOf": [
+    {
+      "if": {
+        "properties": {
+          "voice_model": {
+            "const": "custom"
+          }
+        }
+      },
+      "then": {
+        "properties": {
+          "voice_model_custom": {
+            "type": "array",
+            "items": {
+              "type": "string"
+            },
+            "title": "Voice Model (Custom)",
+            "x-link": "[Supported Voice Model](https://docs.venice.ai/api-reference/endpoint/audio/speech#body-voice)",
+            "description": "You can add one or more custom voice models.",
+            "default": [
+              "af_heart",
+              "bm_lewis"
+            ]
+          }
+        },
+        "required": [
+          "voice_model_custom"
+        ]
+      }
+    },
+    {
+      "if": {
+        "allOf": [
+          {
+            "properties": {
+              "enabled": {
+                "const": true
+              }
+            }
+          },
+          {
+            "properties": {
+              "api_key_provider": {
+                "const": "agent_owner"
+              }
+            }
+          }
+        ]
+      },
+      "then": {
+        "properties": {
+          "api_key": {
+            "type": "string",
+            "title": "Venice API Key",
+            "x-link": "[Get your API key](https://venice.ai/)",
+            "x-sensitive": true,
+            "description": "API Key for authenticating with the Venice AI API."
+          },
+          "rate_limit_number": {
+            "type": "integer",
+            "title": "Rate Limit Number",
+            "description": "Number of requests allowed per time window."
+          },
+          "rate_limit_minutes": {
+            "type": "integer",
+            "title": "Rate Limit Minutes",
+            "description": "Time window in minutes for rate limiting."
+          }
+        },
+        "required": [
+          "api_key"
+        ]
+      }
+    }
+  ],
+  "additionalProperties": true
+}

intentkit/skills/venice_audio/venice_audio.py

@@ -1,15 +1,14 @@
 import hashlib
 import json
 import logging
-from typing import Any, Dict, Optional, Type
+from typing import Any
 
 import httpx
-from pydantic import BaseModel, Field
+from pydantic import BaseModel
 
-from intentkit.abstracts.skill import SkillStoreABC
 from intentkit.skills.venice_audio.base import VeniceAudioBaseTool
 from intentkit.skills.venice_audio.input import AllowedAudioFormat, VeniceAudioInput
-from intentkit.utils.s3 import FileType, store_file_bytes
+from intentkit.utils.s3 import store_file
 
 logger = logging.getLogger(__name__)
 
@@ -33,22 +32,19 @@ class VeniceAudioTool(VeniceAudioBaseTool):
         "Requires input text. Optional parameters include speed (0.25-4.0, default 1.0) "
         "and audio format (mp3, opus, aac, flac, wav, pcm, default mp3)."
     )
-    args_schema: Type[BaseModel] = VeniceAudioInput
-    skill_store: SkillStoreABC = Field(
-        description="The skill store instance for accessing system/agent configurations and persisting data."
-    )
+    args_schema: type[BaseModel] = VeniceAudioInput
 
     async def _arun(
         self,
-        input: str,
+        voice_input: str,
         voice_model: str,
-        speed: Optional[float] = 1.0,
-        response_format: Optional[AllowedAudioFormat] = "mp3",
+        speed: float | None = 1.0,
+        response_format: AllowedAudioFormat | None = "mp3",
         **kwargs,  # type: ignore
-    ) -> Dict[str, Any]:
+    ) -> dict[str, Any]:
         """
         Generates audio using the configured voice model via Venice AI TTS /audio/speech endpoint.
-        Stores the resulting audio using store_file_bytes.
+        Stores the resulting audio using the generic S3 helper.
         Returns a dictionary containing audio details on success, or API error details on failure.
         """
         context = self.get_context()
@@ -96,9 +92,9 @@ class VeniceAudioTool(VeniceAudioBaseTool):
             await self.apply_rate_limit(context)
 
             # --- Prepare API Call ---
-            payload: Dict[str, Any] = {
+            payload: dict[str, Any] = {
                 "model": tts_model_id,
-                "input": input,
+                "input": voice_input,
                 "voice": voice_model,
                 "response_format": final_response_format,
                 "speed": speed if speed is not None else 1.0,
@@ -155,11 +151,32 @@ class VeniceAudioTool(VeniceAudioBaseTool):
                     key = f"{self.category}/{voice_model}/{audio_hash}.{file_extension}"
 
                     size_limit = 1024 * 20  # 20Mb Size limit
-                    stored_url = await store_file_bytes(
-                        file_bytes=audio_bytes,
+                    audio_size = len(audio_bytes)
+                    if audio_size > size_limit:
+                        message = f"Generated audio exceeds the allowed size of {size_limit} bytes."
+                        logger.error(
+                            "Failed to store audio (Voice: %s): %s",
+                            voice_model,
+                            message,
+                        )
+                        return {
+                            "error": True,
+                            "error_type": "FileSizeLimitExceeded",
+                            "message": message,
+                            "voice_model": voice_model,
+                            "requested_format": final_response_format,
+                        }
+
+                    mime_type = (
+                        content_type_header.split(";", 1)[0].strip()
+                        if content_type_header
+                        else None
+                    )
+                    stored_url = await store_file(
+                        content=audio_bytes,
                         key=key,
-                        file_type=FileType.AUDIO,
-                        size_limit_bytes=size_limit,
+                        content_type=mime_type,
+                        size=audio_size,
                     )
 
                     if not stored_url:
@@ -182,12 +199,12 @@ class VeniceAudioTool(VeniceAudioBaseTool):
                     return {
                         "audio_url": stored_url,
                         "audio_bytes_sha256": audio_hash,
-                        "content_type": content_type_header,
+                        "content_type": mime_type or content_type_header,
                         "voice_model": voice_model,
                         "tts_engine": tts_model_id,
                         "speed": speed if speed is not None else 1.0,
                         "response_format": final_response_format,
-                        "input_text_length": len(input),
+                        "input_text_length": len(voice_input),
                         "error": False,
                         "status_code": response.status_code,
                     }