mirror of
https://github.com/calesthio/OpenMontage.git
synced 2026-08-05 15:20:40 +08:00
34d1053526
Add gemini_omni_video, a native Gemini API provider wrapping gemini-omni-flash-preview via the Interactions API. Text-to-video, image/reference-to-video with <FIRST_FRAME>/<IMAGE_REF_N> prompt tags, and stateful edit_video turns via previous_interaction_id — the only provider in the fleet that can refine a clip without regenerating it. Reuses the existing GOOGLE_API_KEY / GEMINI_API_KEY, so one Google key now unlocks images, TTS, and video. - New Layer 3 skill .agents/skills/gemini-omni (prompting, edit-loop rules, tag/timecode syntax, preview limits) sourced from official Google docs; linked via agent_skills and the AGENT_GUIDE Layer 3 map - ai-video-gen gains the Gemini API gateway row + editing pointer - veo_video/sora_video fallback lists and video_selector agent_skills reference the new provider; quality_score 0.85 with rationale - Contract tests: registry discovery, selector routing, status from env keys, uri + inline delivery, edit turns, typed image parts, store=false editability, cost clamp
63 lines
3.6 KiB
Plaintext
63 lines
3.6 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
|
|
FAL_AI_API_KEY= # Alias for FAL_KEY (some SDKs/docs use this name); either one is read.
|
|
|
|
# --- Replicate ---
|
|
REPLICATE_API_TOKEN= # 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
|
|
|
|
# --- Higgsfield ---
|
|
HIGGSFIELD_API_KEY= # Higgsfield Cloud key (higgsfield_video). Pair with the secret below,
|
|
HIGGSFIELD_API_SECRET= # or use the combined HIGGSFIELD_KEY="<key>:<secret>" form instead.
|
|
# HIGGSFIELD_KEY= # Combined key:secret — set this INSTEAD of the _KEY/_SECRET pair if you prefer.
|
|
|
|
# --- Google (one key unlocks image gen + TTS + video) ---
|
|
GOOGLE_API_KEY= # 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
|
|
# 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.
|
|
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
|
|
|
|
# --- DashScope (Alibaba Cloud Bailian) ---
|
|
DASHSCOPE_API_KEY= # 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/
|
|
|
|
# --- 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)
|