Configuration

March 2, 2026 ยท View on GitHub

MoneyPrinter reads configuration from .env (project root).

Use .env.example as your template.

Required

VariableDescription
TIKTOK_SESSION_IDTikTok session cookie (sessionid) used for TTS voice endpoint calls.
PEXELS_API_KEYAPI key used to fetch stock video clips.

Optional

VariableDescriptionDefault
IMAGEMAGICK_BINARYAbsolute path to ImageMagick executable. If empty, auto-detected from PATH.auto-detect
OLLAMA_BASE_URLOllama server base URL used for model listing and chat generation.http://localhost:11434
OLLAMA_MODELFallback model if frontend does not send a model value.llama3.1:8b
ASSEMBLY_AI_API_KEYIf set, subtitles are generated with AssemblyAI; otherwise local subtitle generation is used.empty
POSTGRES_DBDatabase name for Docker Postgres service.moneyprinter
POSTGRES_USERDatabase user for Docker Postgres service.moneyprinter
POSTGRES_PASSWORDDatabase password for Docker Postgres service.moneyprinter
DATABASE_URLSQLAlchemy DSN used by API and worker (postgresql+psycopg://... or sqlite:///...).sqlite:///moneyprinter.db

Notes

  • Ollama models shown in the frontend are fetched from backend endpoint /api/models, which queries OLLAMA_BASE_URL/api/tags.
  • Pull models before use, for example:
ollama pull llama3.1:8b
  • If ImageMagick is not discovered automatically, set IMAGEMAGICK_BINARY explicitly.
  • New architecture uses a database-backed job queue. In Docker, use Postgres via DATABASE_URL.