mirror of
https://github.com/calesthio/OpenMontage.git
synced 2026-08-12 11:43:54 +08:00
fabc0e7088
- openai_image: enum narrowed to ["gpt-image-2"]; DALL-E code path, sizes (1024x1792/1792x1024) and qualities (standard/hd) removed; estimate_cost updated to real GPT Image 2 pricing ($0.006/$0.053/$0.211 at 1024x1024) - image_gen (deprecated but callable): default dall-e-3 -> gpt-image-2; drop response_format="b64_json", which GPT image models reject; update pricing - docs/skills sweep: scrub retired-model references from README (en/zh), .env.example, docs/PROVIDERS.md (incl. pricing table + deprecation note), docs/ARCHITECTURE.md, AGENT_GUIDE.md, skills/creative/*, 14 pipeline director skills, and tests/qa/QA_PLAN.md Source: https://developers.openai.com/api/docs/deprecations proofread by fable 5 + codex
46 lines
2.5 KiB
Plaintext
46 lines
2.5 KiB
Plaintext
# OpenMontage - Environment Variables
|
|
# Copy this to .env and fill in your keys
|
|
|
|
# --- Image + video gateway ---
|
|
FAL_KEY= # FLUX images, Google Veo video, Kling video, MiniMax video, Recraft images
|
|
# Get one at https://fal.ai/dashboard/keys
|
|
|
|
# --- Google (one key unlocks image gen + TTS) ---
|
|
GOOGLE_API_KEY= # Google Imagen images, Google Cloud TTS (700+ voices, 50+ languages)
|
|
# Get one at https://aistudio.google.com/apikey
|
|
# Alternative to the API key: service-account JSON auth.
|
|
# TTS uses Cloud Text-to-Speech; Imagen routes to Vertex AI.
|
|
GOOGLE_APPLICATION_CREDENTIALS= # path to a service-account JSON key file
|
|
GOOGLE_CLOUD_PROJECT= # GCP project id (required for Imagen via Vertex AI)
|
|
GOOGLE_CLOUD_LOCATION= # Vertex AI region, default us-central1
|
|
|
|
# --- Voice ---
|
|
ELEVENLABS_API_KEY= # TTS narration, music generation, sound effects
|
|
OPENAI_API_KEY= # OpenAI TTS fallback and GPT Image 2 image generation
|
|
XAI_API_KEY= # Grok image generation/editing and Grok video generation
|
|
DOUBAO_SPEECH_API_KEY= # Volcengine Doubao Speech TTS (new console API Key)
|
|
DOUBAO_SPEECH_VOICE_TYPE= # Default Doubao speaker/voice type, e.g. zh_female_vv_uranus_bigtts
|
|
# Piper local voices do not require env vars; install `piper-tts` via pip
|
|
|
|
# --- Music ---
|
|
SUNO_API_KEY= # Suno AI music generation (full songs, instrumentals, any genre)
|
|
|
|
# --- Video Generation ---
|
|
HEYGEN_API_KEY= # HeyGen API (VEO, Sora, Runway, Kling, Seedance via single key)
|
|
RUNWAY_API_KEY= # Runway Gen-4 (direct API, alternative to fal.ai routing)
|
|
VIDEO_GEN_LOCAL_ENABLED= # Set to "true" for local video gen (needs GPU + diffusers)
|
|
VIDEO_GEN_LOCAL_MODEL= # Local model: wan2.1-1.3b, wan2.1-14b, hunyuan-1.5, ltx2-local, cogvideo-5b
|
|
MODAL_LTX2_ENDPOINT_URL= # Modal self-hosted LTX-2 endpoint (optional)
|
|
|
|
# --- Stock Media ---
|
|
PEXELS_API_KEY= # Pexels stock footage/images (free)
|
|
PIXABAY_API_KEY= # Pixabay stock footage/images (free)
|
|
UNSPLASH_ACCESS_KEY= # Unsplash stock images (free developer key)
|
|
|
|
# --- Analysis ---
|
|
HF_TOKEN= # HuggingFace token — enables speaker diarization in transcriber
|
|
|
|
# --- Avatar (local installs) ---
|
|
# WAV2LIP_PATH= # Path to cloned Wav2Lip repo (for lip sync)
|
|
# SADTALKER_PATH= # Path to cloned SadTalker repo (for talking head avatars)
|