Audio version — Estimated duration: 2 min 45 sec
Requirements
| Requirement | Minimum |
|---|---|
| Python | 3.10+ |
| Disk | ~500 MB for Piper models |
Online mode (default)
Minimal install — just the APIs:
pip install edge-tts openaiSet your Cerebras API key:
$env:CEREBRAS_API_KEY = "your-key-here"Local TTS mode (Piper + GPU)
Add onnxruntime and the Piper wrapper:
pip install piper-tts onnxruntime-gpu huggingface-hub mutagen
onnxruntime-gpuincludes CPU fallback. You do not need a separateonnxruntimeinstall.
Piper models auto-download to models/ on first use from Hugging Face.
Local LLM mode (llama.cpp)
No extra pip packages. Run a llama.cpp server:
llama-server -m your-model.gguf --port 8080The pipeline expects it at http://localhost:8080/v1.
For GPU acceleration on local TTS:
pip install onnxruntime-gpuForce CPU fallback at runtime with --cpu.
Next: Quickstart