Files
OpenMontage/.env.example
2026-08-03 02:14:01 -07:00

107 lines
4.2 KiB
Plaintext

# OpenMontage - Environment Variables
# Copy this to .env and fill in your keys
# --- Image + video gateway ---
# FLUX images, Google Veo video, Kling video, MiniMax video, Recraft images.
# Get one at https://fal.ai/dashboard/keys
FAL_KEY=
# Alias for FAL_KEY (some SDKs/docs use this name); either one is read.
FAL_AI_API_KEY=
# --- Replicate ---
# Replicate-hosted video gen (seedance_replicate). Needed to make the
# Replicate-backed Seedance path selectable alongside the fal.ai one.
# Get one at https://replicate.com/account/api-tokens
REPLICATE_API_TOKEN=
# --- Higgsfield ---
# Higgsfield Cloud key (higgsfield_video). Pair with the secret below,
# or use the combined HIGGSFIELD_KEY="<key>:<secret>" form instead.
HIGGSFIELD_API_KEY=
HIGGSFIELD_API_SECRET=
# HIGGSFIELD_KEY= # Combined key:secret — set this INSTEAD of the _KEY/_SECRET pair if you prefer.
# --- Kling official direct API ---
# Official Kling API key; enables video, image, TTS, avatar, lip sync.
KLING_API_KEY=
# Optional endpoint override; leave blank for default https://api-singapore.klingai.com
# Mainland China accounts can use https://api-beijing.klingai.com
KLING_API_BASE_URL=
# --- Google (one key unlocks image gen + TTS + video) ---
# Google Imagen images, Google Cloud TTS (700+ voices, 50+ languages),
# Gemini Omni video (generation + conversational editing, paid tier).
# Get one at https://aistudio.google.com/apikey
GOOGLE_API_KEY=
# GEMINI_API_KEY= # Alias for GOOGLE_API_KEY (takes precedence when both are set)
# Alternative to the API key: service-account JSON auth.
# TTS uses Cloud Text-to-Speech; Imagen routes to Vertex AI.
# Path to a service-account JSON key file.
GOOGLE_APPLICATION_CREDENTIALS=
# GCP project id (required for Imagen via Vertex AI).
GOOGLE_CLOUD_PROJECT=
# Vertex AI region, default us-central1.
GOOGLE_CLOUD_LOCATION=
# --- Voice ---
# TTS narration, music generation, sound effects.
ELEVENLABS_API_KEY=
# OpenAI TTS fallback and GPT Image 2 image generation.
OPENAI_API_KEY=
# Grok image generation/editing and Grok video generation.
XAI_API_KEY=
# Volcengine Doubao Speech TTS (new console API Key).
DOUBAO_SPEECH_API_KEY=
# Default Doubao speaker/voice type, e.g. zh_female_vv_uranus_bigtts.
DOUBAO_SPEECH_VOICE_TYPE=
# Piper local voices do not require env vars; install `piper-tts` via pip
# --- DashScope (Alibaba Cloud Bailian) ---
# Qwen image gen (qwen-image-2.0-pro), TTS (qwen3-tts-flash), ASR with word timestamps (qwen3-asr-flash-filetrans).
# Get one at https://dashscope.aliyun.com/
DASHSCOPE_API_KEY=
# --- Music ---
# Suno AI music generation (full songs, instrumentals, any genre).
SUNO_API_KEY=
# --- Video Generation ---
# HeyGen API (VEO, Sora, Runway, Kling, Seedance via single key).
HEYGEN_API_KEY=
# Runway Gen-4 (direct API, alternative to fal.ai routing).
RUNWAY_API_KEY=
# Volcengine Jimeng (即梦 AI) video generation via official API (HMAC-SHA256 V4 signing).
VOLC_ACCESSKEY=
# Secret Access Key paired with VOLC_ACCESSKEY. Get both at https://console.volcengine.com/iam/keymanage
VOLC_SECRETKEY=
# Set to "true" for local video gen (needs GPU + diffusers).
VIDEO_GEN_LOCAL_ENABLED=
# Local model: wan2.1-1.3b, wan2.1-14b, hunyuan-1.5, ltx2-local, cogvideo-5b.
VIDEO_GEN_LOCAL_MODEL=
# Modal self-hosted LTX-2 endpoint (optional).
MODAL_LTX2_ENDPOINT_URL=
# --- Stock Media ---
# Pexels stock footage/images (free).
PEXELS_API_KEY=
# Pixabay stock footage/images (free).
PIXABAY_API_KEY=
# Unsplash stock images (free developer key).
UNSPLASH_ACCESS_KEY=
# --- Analysis ---
# HuggingFace token — enables speaker diarization in transcriber.
HF_TOKEN=
# Speech-to-text: optional Azure AI Speech (Fast Transcription). When set, the
# agent prefers azure_stt for cloud STT; the local faster-whisper transcriber
# remains the default offline path.
# Azure AI Speech resource key ('Keys and Endpoint' page).
AZURE_SPEECH_KEY=
# Speech resource region, e.g. eastus.
AZURE_SPEECH_REGION=
# AZURE_SPEECH_ENDPOINT= # Optional: full custom endpoint URL (overrides region)
# --- Avatar (local installs) ---
# WAV2LIP_PATH= # Path to cloned Wav2Lip repo (for lip sync)
# SADTALKER_PATH= # Path to cloned SadTalker repo (for talking head avatars)