[pull] master from Comfy-Org:master

.coderabbit.yaml

@@ -0,0 +1,114 @@
+# yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json
+language: "en-US"
+early_access: false
+
+reviews:
+  profile: "chill"
+  request_changes_workflow: false
+  high_level_summary: false
+  poem: false
+  review_status: false
+  review_details: false
+  commit_status: true
+  collapse_walkthrough: true
+  changed_files_summary: false
+  sequence_diagrams: false
+  estimate_code_review_effort: false
+  assess_linked_issues: false
+  related_issues: false
+  related_prs: false
+  suggested_labels: false
+  auto_apply_labels: false
+  suggested_reviewers: false
+  auto_assign_reviewers: false
+  in_progress_fortune: false
+  enable_prompt_for_ai_agents: true
+
+  path_filters:
+    - "!comfy_api_nodes/apis/**"
+    - "!**/generated/*.pyi"
+    - "!.ci/**"
+    - "!script_examples/**"
+    - "!**/__pycache__/**"
+    - "!**/*.ipynb"
+    - "!**/*.png"
+    - "!**/*.bat"
+
+  path_instructions:
+    - path: "comfy/**"
+      instructions: |
+        Core ML/diffusion engine. Focus on:
+        - Backward compatibility (breaking changes affect all custom nodes)
+        - Memory management and GPU resource handling
+        - Performance implications in hot paths
+        - Thread safety for concurrent execution
+    - path: "comfy_api_nodes/**"
+      instructions: |
+        Third-party API integration nodes. Focus on:
+        - No hardcoded API keys or secrets
+        - Proper error handling for API failures (timeouts, rate limits, auth errors)
+        - Correct Pydantic model usage
+        - Security of user data passed to external APIs
+    - path: "comfy_extras/**"
+      instructions: |
+        Community-contributed extra nodes. Focus on:
+        - Consistency with node patterns (INPUT_TYPES, RETURN_TYPES, FUNCTION, CATEGORY)
+        - No breaking changes to existing node interfaces
+    - path: "comfy_execution/**"
+      instructions: |
+        Execution engine (graph execution, caching, jobs). Focus on:
+        - Caching correctness
+        - Concurrent execution safety
+        - Graph validation edge cases
+    - path: "nodes.py"
+      instructions: |
+        Core node definitions (2500+ lines). Focus on:
+        - Backward compatibility of NODE_CLASS_MAPPINGS
+        - Consistency of INPUT_TYPES return format
+    - path: "alembic_db/**"
+      instructions: |
+        Database migrations. Focus on:
+        - Migration safety and rollback support
+        - Data preservation during schema changes
+
+  auto_review:
+    enabled: true
+    auto_incremental_review: true
+    drafts: true
+
+  finishing_touches:
+    docstrings:
+      enabled: false
+    unit_tests:
+      enabled: false
+
+  tools:
+    ruff:
+      enabled: true
+    pylint:
+      enabled: false
+    flake8:
+      enabled: false
+    gitleaks:
+      enabled: true
+    shellcheck:
+      enabled: false
+    markdownlint:
+      enabled: false
+    yamllint:
+      enabled: false
+    languagetool:
+      enabled: false
+    github-checks:
+      enabled: true
+      timeout_ms: 90000
+    ast-grep:
+      essential_rules: true
+
+chat:
+  auto_reply: true
+
+knowledge_base:
+  opt_out: false
+  learnings:
+    scope: "auto"

comfy_api_nodes/apis/elevenlabs.py

@@ -0,0 +1,88 @@
+from pydantic import BaseModel, Field
+
+
+class SpeechToTextRequest(BaseModel):
+    model_id: str = Field(...)
+    cloud_storage_url: str = Field(...)
+    language_code: str | None = Field(None, description="ISO-639-1 or ISO-639-3 language code")
+    tag_audio_events: bool | None = Field(None, description="Annotate sounds like (laughter) in transcript")
+    num_speakers: int | None = Field(None, description="Max speakers predicted")
+    timestamps_granularity: str = Field(default="word", description="Timing precision: none, word, or character")
+    diarize: bool | None = Field(None, description="Annotate which speaker is talking")
+    diarization_threshold: float | None = Field(None, description="Speaker separation sensitivity")
+    temperature: float | None = Field(None, description="Randomness control")
+    seed: int = Field(..., description="Seed for deterministic sampling")
+
+
+class SpeechToTextWord(BaseModel):
+    text: str = Field(..., description="The word text")
+    type: str = Field(default="word", description="Type of text element (word, spacing, etc.)")
+    start: float | None = Field(None, description="Start time in seconds (when timestamps enabled)")
+    end: float | None = Field(None, description="End time in seconds (when timestamps enabled)")
+    speaker_id: str | None = Field(None, description="Speaker identifier when diarization is enabled")
+    logprob: float | None = Field(None, description="Log probability of the word")
+
+
+class SpeechToTextResponse(BaseModel):
+    language_code: str = Field(..., description="Detected or specified language code")
+    language_probability: float | None = Field(None, description="Confidence of language detection")
+    text: str = Field(..., description="Full transcript text")
+    words: list[SpeechToTextWord] | None = Field(None, description="Word-level timing information")
+
+
+class TextToSpeechVoiceSettings(BaseModel):
+    stability: float | None = Field(None, description="Voice stability")
+    similarity_boost: float | None = Field(None, description="Similarity boost")
+    style: float | None = Field(None, description="Style exaggeration")
+    use_speaker_boost: bool | None = Field(None, description="Boost similarity to original speaker")
+    speed: float | None = Field(None, description="Speech speed")
+
+
+class TextToSpeechRequest(BaseModel):
+    text: str = Field(..., description="Text to convert to speech")
+    model_id: str = Field(..., description="Model ID for TTS")
+    language_code: str | None = Field(None, description="ISO-639-1 or ISO-639-3 language code")
+    voice_settings: TextToSpeechVoiceSettings | None = Field(None, description="Voice settings")
+    seed: int = Field(..., description="Seed for deterministic sampling")
+    apply_text_normalization: str | None = Field(None, description="Text normalization mode: auto, on, off")
+
+
+class TextToSoundEffectsRequest(BaseModel):
+    text: str = Field(..., description="Text prompt to convert into a sound effect")
+    duration_seconds: float = Field(..., description="Duration of generated sound in seconds")
+    prompt_influence: float = Field(..., description="How closely generation follows the prompt")
+    loop: bool | None = Field(None, description="Whether to create a smoothly looping sound effect")
+
+
+class AddVoiceRequest(BaseModel):
+    name: str = Field(..., description="Name that identifies the voice")
+    remove_background_noise: bool = Field(..., description="Remove background noise from voice samples")
+
+
+class AddVoiceResponse(BaseModel):
+    voice_id: str = Field(..., description="The newly created voice's unique identifier")
+
+
+class SpeechToSpeechRequest(BaseModel):
+    model_id: str = Field(..., description="Model ID for speech-to-speech")
+    voice_settings: str = Field(..., description="JSON string of voice settings")
+    seed: int = Field(..., description="Seed for deterministic sampling")
+    remove_background_noise: bool = Field(..., description="Remove background noise from input audio")
+
+
+class DialogueInput(BaseModel):
+    text: str = Field(..., description="Text content to convert to speech")
+    voice_id: str = Field(..., description="Voice identifier for this dialogue segment")
+
+
+class DialogueSettings(BaseModel):
+    stability: float | None = Field(None, description="Voice stability (0-1)")
+
+
+class TextToDialogueRequest(BaseModel):
+    inputs: list[DialogueInput] = Field(..., description="List of dialogue segments")
+    model_id: str = Field(..., description="Model ID for dialogue generation")
+    language_code: str | None = Field(None, description="ISO-639-1 language code")
+    settings: DialogueSettings | None = Field(None, description="Voice settings")
+    seed: int | None = Field(None, description="Seed for deterministic sampling")
+    apply_text_normalization: str | None = Field(None, description="Text normalization mode: auto, on, off")