# Python API

## `InflectTTS(model_dir, device="cpu")`

Loads one released checkpoint and its configuration. Construct the engine once and reuse it for multiple utterances.

## `synthesize(text, *, speed=1.0, variation=0.667, seed=0)`

Returns a mono `numpy.float32` waveform at 24 kHz. Empty text raises `ValueError`. `speed` must be between `0.5` and `2.0`; `variation` must be between `0.0` and `1.0`. Long input is split at punctuation-aware boundaries, and each chunk uses `seed + chunk_index`.

## `save(text, output, **kwargs)`

Synthesizes and writes a WAV file, creating parent directories as needed. It returns the output `Path`.

```python
from inference import InflectTTS

tts = InflectTTS(".", device="cpu")
waveform = tts.synthesize("A compact model can still speak clearly.", seed=7)
tts.save("This is written directly to disk.", "out.wav", seed=7)
```

The API is intentionally small. It does not expose speaker cloning, streaming state, SSML, or language switching in the v2 launch package.