mirror of
https://github.com/calesthio/OpenMontage.git
synced 2026-08-05 15:20:40 +08:00
4327000433
Two new provider tools following the BaseTool pattern with auto-discovery: - google_imagen: Imagen 4 image generation via Generative Language REST API - google_tts: Google Cloud TTS with 700+ voices across 50+ languages Both share GOOGLE_API_KEY env var. Selectors auto-discover them — no selector code changes needed. Docs and contract tests updated. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
37 lines
1.8 KiB
Plaintext
37 lines
1.8 KiB
Plaintext
# OpenMontage - Environment Variables
|
|
# Copy this to .env and fill in your keys
|
|
|
|
# --- fal.ai (one key unlocks the most tools) ---
|
|
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
|
|
|
|
# --- Voice ---
|
|
ELEVENLABS_API_KEY= # TTS narration, music generation, sound effects
|
|
OPENAI_API_KEY= # OpenAI TTS fallback and DALL-E image generation
|
|
# 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)
|
|
|
|
# --- 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)
|