@leejungkiin/awkit 1.3.8 → 1.4.2

package/skills/short-maker/scripts/google-flow-cli/docs/specs/REQUIREMENTS.md

@@ -0,0 +1,22 @@
+# Requirements
+
+## 1. Image-First Storyboarding
+- Generates zero-cost images for each scene/segment before generating videos.
+- Used to validate prompts, style, character consistency, and scene composition.
+
+## 2. Video Generation Workflow
+- Creates videos strictly upon explicit approval of the image storyboard.
+- Short iteration loops (single segments) favored to avoid batch errors.
+
+## 3. Voiceover (TTS) Pipeline
+- Mandatory use of `lucylab_tts.py` for TTS generation (JSON-RPC).
+- Local macOS TTS (`say`) is strictly forbidden.
+- Requires `LUCYLAB_BEARER` environment variable for token safety.
+
+## 4. A/V Composition
+- Post-process merging of generated video and audio using `ffmpeg`.
+- Standardized output naming convention: `outputs/.../script-full-vo.mp4`.
+
+## 5. Artifact Management
+- Outputs generated sequentially under `outputs/` folder.
+- Voice library caching strictly regulated to `voices_library.json`.

package/skills/short-maker/scripts/google-flow-cli/docs/specs/ROADMAP.md

@@ -0,0 +1,16 @@
+# Roadmap
+
+## Phase 1: Environment & Tooling Verification
+- [ ] Initialize project specifications and Antigravity tracking (Symphony, Brain).
+- [ ] Verify local Python dependencies and `lucylab_tts.py` tool access.
+- [ ] Verify FFmpeg installation and access.
+
+## Phase 2: TTS & Pipeline Groundwork
+- [ ] Establish environment variables integration (`LUCYLAB_BEARER`).
+- [ ] Test compact JSON voice library retrieval.
+- [ ] Test standalone script rendering (`script.txt` -> `outputs/tts-lucylab`).
+
+## Phase 3: Visual & Final Compositing Generation
+- [ ] Image storyboard extraction and generation workflow.
+- [ ] Video segment generation loop.
+- [ ] Master A/V compositing via FFmpeg.

package/skills/short-maker/scripts/google-flow-cli/docs/specs/TECH-SPEC.md

@@ -0,0 +1,13 @@
+# Technical Specifications
+
+## Architecture Decisions
+- **AD-1: Cost Model Gatekeeping**
+  - Image validation step must pre-empt any video API call. Video generation takes place only upon explicit approval.
+- **AD-2: Strict Output Segregation**
+  - Scripts and generated artifacts reside purely within `outputs/`.
+- **AD-3: Modular Voice Library**
+  - Use compact `voices_library.json` catalog containing only `{id,name,description,tag}` for context efficiency.
+
+## Constraints & Security
+- **Config & Tokens**: Bearer tokens are strictly ENV-based (`LUCYLAB_BEARER`). No static token commits or log files exposing tokens in the repo.
+- **Tooling Platform**: Python for automation scripts (`lucylab_tts.py`); `ffmpeg` required as system dependency for A/V composition.

package/skills/short-maker/scripts/google-flow-cli/gflow/__init__.py

@@ -0,0 +1,3 @@
+"""gflow - A command-line interface to Google Flow (AI image & video generation)."""
+
+__version__ = "0.1.0"

package/skills/short-maker/scripts/google-flow-cli/gflow/api/__init__.py

@@ -0,0 +1,19 @@
+"""Google Flow API client."""
+
+from .client import FlowClient, FlowAPIError, FlowRecaptchaError
+from .models import (
+    Asset,
+    AssetType,
+    GenerateImageRequest,
+    GenerateVideoRequest,
+)
+
+__all__ = [
+    "FlowClient",
+    "FlowAPIError",
+    "FlowRecaptchaError",
+    "Asset",
+    "AssetType",
+    "GenerateImageRequest",
+    "GenerateVideoRequest",
+]