OpenMontage/.env.example

# 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=

# --- MiniMax official direct API ---
# First-party image generation (image-01 / image-01-live).
# Get one at https://platform.minimax.io/user-center/basic-information/interface-key
MINIMAX_API_KEY=
# Optional: global (default) or cn.
MINIMAX_REGION=global

# --- 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=
# fish.audio TTS (s1 / s2-pro / s2.1-pro, reference_id voice cloning).
FISH_AUDIO_API_KEY=
# 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=

# --- Tencent Hunyuan TokenHub API ---
# Tencent Hunyuan (腾讯混元) image and cloud video generation via TokenHub
# (Bearer token).
# Get it at https://console.cloud.tencent.com/tokenhub.
TENCENT_TOKENHUB_API_KEY=

# --- Music ---
# Suno AI music generation (full songs, instrumentals, any genre).
SUNO_API_KEY=

# --- Video Generation ---
# Volcengine Ark direct Seedance 2.0 API key body (without the "Bearer " prefix).
# Get one at https://console.volcengine.com/ark/region:cn-beijing/apiKey
ARK_API_KEY=
# Optional overrides; uncomment only when needed.
# ARK_SEEDANCE_MODEL=doubao-seedance-2-0-260128
# ARK_BASE_URL=https://ark.cn-beijing.volces.com/api/v3
# ARK_CNY_PER_USD=7.2
# 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: optional Azure AI Speech. One key/region unlocks both directions —
# azure_stt (Fast Transcription cloud STT) and azure_tts (neural cloud TTS).
# The local faster-whisper transcriber / piper_tts remain the default offline paths.
AZURE_SPEECH_KEY=
AZURE_SPEECH_REGION=
# AZURE_SPEECH_ENDPOINT=     # Optional: full custom STT endpoint URL (overrides region)
# AZURE_TTS_ENDPOINT=        # Optional: full custom TTS host (e.g. https://<region>.tts.speech.microsoft.com)

# --- Avatar (local installs) ---
# WAV2LIP_PATH=              # Path to cloned Wav2Lip repo (for lip sync)
# SADTALKER_PATH=            # Path to cloned SadTalker repo (for talking head avatars)