it_IT-serena-high

it_IT-serena-high — Piper voice (Italian)

Custom Italian voice for Piper, trained from the committa/serena-synthetic-it-28h dataset (Qwen3-TTS synthetic voice).

• Language: Italian (it) — neutral Standard Italian (no regional accent)
• Voice: female ("serena")
• Sample rate: 22050 Hz
• Quality: high
• Files: it_IT-serena-high.onnx + it_IT-serena-high.onnx.json (must stay together)

License

CC-BY-4.0 — this model is derived from committa/serena-synthetic-it-28h.

Recommended inference settings

The .onnx.json already embeds these defaults; the CLI uses them automatically. They were chosen after stability testing: the Piper stock defaults (0.667 / 0.8) tend to swallow phonemes (e.g. /r/ in "portato").

Sample

<audio controls src="https://huggingface.co/committa/it_IT-serena-high/resolve/main/samples/speaker_0.mp3"></audio>

CLI usage

piper -m it_IT-serena-high.onnx < text.txt

Explicit overrides (optional):

piper -m it_IT-serena-high.onnx --noise-scale 0.6 --noise-w 0.4 < text.txt

Home Assistant (piper add-on)

The Home Assistant add-on ignores the .onnx.json settings and always passes its own options, whose defaults (noise_scale 0.667, noise_w 0.333) are NOT optimal for this voice. For the best quality set in the add-on options:

• noise_scale: 0.6
• length_scale: 1.0
• noise_w: 0.4
• sentence_silence: 0.2 (optional; add-on default is 0.0)

Notes

• Pronunciation of rare vocabulary (<10 occurrences in training data) can be off; fix with espeak-ng rules if needed.
• The training checkpoint (base for finetuning other Italian voices) is published at: https://huggingface.co/committa/it_IT-serena-high-checkpoint