Metadata-Version: 2.4
Name: tlnw-text-to-podcast
Version: 0.4.0
Summary: Generate podcast audio/video from prompt files using pluggable TTS providers
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: python-dotenv>=1.0.0
Requires-Dist: google-genai>=1.0.0

# tlnw-text-to-podcast

Python CLI module for generating multi-speaker podcast audio/video from prompt files and JSON scene configs.

## Install

```bash
pip install .
```

## CLI

```bash
text-to-podcast --help
```

### Options

- `--help`
- `--debug`
- `--version`
- `--provider`
- `--file`
- `--output`
- `--input-file`
- `--scene`
- `--model`
- `--force`

### Gemini TTS models

- Default model: `gemini-2.5-flash-tts`
- Supported Gemini TTS models: `gemini-2.5-flash-lite-preview-tts`, `gemini-2.5-flash-tts`, `gemini-2.5-pro-tts`, `gemini-3.1-flash-tts-preview`
- Backward compatibility: `gemini-2.5-flash-preview-tts` is automatically mapped to `gemini-2.5-flash-tts`

## Provider modules

The TTS provider implementation is now split into a dedicated package under `tlnw_text_to_podcast/providers`:

- `base.py` for the shared `TTSProvider` abstraction
- `gemini.py` for Gemini-specific generation logic
- `factory.py` for provider selection and creation

These modules are included in the published Python package via the package discovery settings in `pyproject.toml`.

## Compatibility

The legacy `text-to-podcast.py` script remains as a compatibility wrapper to the packaged CLI.
