Finrandojin / alexandria-audiobook

What it does

• Local & Cloud LLM Support. Use any OpenAI-compatible API (LM Studio, Ollama, OpenAI, etc.)
• Automatic Script Annotation. LLM parses text into JSON with speakers, dialogue, and TTS instruct directions
• LLM Script Review. Optional second LLM pass that fixes common annotation errors: strips attribution tags from dialogue, splits misattributed narration/dialogue, merges over-split narrator entries, and validates instruct fields
• Persona Generation. LLM analyzes the script to create voice descriptions for each character, then generates reference audio via VoiceDesign and assigns clone voices automatically — one click to go from script to fully-voiced cast
• Speaker Aliases. Map multiple speaker names to the same voice (e.g. "YOUNG ELENA" → "ELENA") so variants share a single voice configuration