DataCraftsmanAustralia/piper-en_AU-librivox-medium

en_AU-librivox-medium

Ten Australian English voices in one Piper (VITS) model. 22,050 Hz mono, ~70M parameters, 77 MB, runs on CPU. Trained on public domain LibriVox recordings. Piper ships no en_AU voice, this fills that gap. The model was trained on a single RTX 6000 Pro over 24 hours, it was still improving slowly when training was paused, so there could still be room to improve.

Voices

Samples all say "I reckon we should head down to the beach before it gets too hot."

id	voice	narrator	gender	sample
0	clancy	son_of_the_exiles	male
1	bindi	jenno	female
2	marlo	lucy_burgoyne_1950_2014	female
3	kirra	magdalena	female
4	angus	algy_pug	male
5	banjo	timothy_ferguson	male
6	flynn	howard_skyman	male
7	matilda	ophelia_darcy	female
8	tully	kirsty_leishman	female
9	willow	jane_bennett	female

Usage

pip install piper-tts
echo "Good on ya mate." | python -m piper -m en_AU-librivox-medium.onnx -s 5 -f out.wav

import wave
from piper import PiperVoice, SynthesisConfig

voice = PiperVoice.load("en_AU-librivox-medium.onnx")
with wave.open("out.wav", "wb") as f:
    voice.synthesize_wav("Good on ya.", f, SynthesisConfig(speaker_id=5))

The .onnx.json is required, it holds the speaker map.

Speech rate. length_scale 1.0 is the trained rate; higher is slower. Set tully and clancy to 1.25 and marlo to 1.08, they rush sometimes, and the samples above are all at 1.0. For serving layers that read the rate from the config instead, configs/ has ready made variants; copy the .onnx alongside under the matching name.

Training

See my training repo on github: https://github.com/DataCraftsmanAustralia/piper-en_AU

Limitations

• Narrow domain. All source text is 19th/early 20th century literature. No modern sentences, URLs, emails or timestamps. Numerals, abbreviations and technical terms are the weakest point.
• Period inflected accent - formal literary reading, not conversational.
• Voice quality is inherited from home recordings: poor mics, volume drift, band limiting. Training more probably won't fix it.
• Transcripts were machine generated (faster-whisper) and uncorrected.
• Not really certain about clancy being Australian, realised after training.

Licence

CC BY 4.0. Commercial use, redistribution and further fine tuning permitted.

Full terms, the ten narrators and provenance: ATTRIBUTION.md.