Voices

28 voices, 10 languages. Every profile is enrolled by this project’s own pipeline from a recording made or released for speech-technology use: personal donations recorded for TTS, and CC0 / CC-BY corpora whose terms allow it. The donor or source, the licence and a sample are named for every voice. The full chain lives in docs/voices/roster/provenance.json: consent basis, reference construction, SHA-256 of profile, reference and sample, and seed.

Open the voice gallery and compare each generated sample with its enrollment reference.

Profiles ship on the Hugging Face repository under voices/, versioned next to the checkpoint they enrol against.

The reference SHA-256 identifies the original WAV used for enrollment. Those source WAVs are not redistributed in the model repository; reference.public_preview names the Opus derivative played on the demo page, not the bytes that were enrolled.

We have evaluated English by ear. We do not speak the other nine languages well enough to judge their naturalness reliably. Feedback from native speakers is very welcome.

voice	language	gender	source	licence
clara	English	F	Kyutai tts-voices	CC0
emma	English	F	Kyutai tts-voices	CC0
henry	English	M	Kyutai tts-voices	CC0
joe	English	M	OHF-Voice donations	CC0
kathleen	English	F	OHF-Voice donations	CC0
lucy	English	F	Kyutai tts-voices	CC0
miles	English	M	Kyutai tts-voices	CC0
oliver	English	M	Kyutai tts-voices	CC0
oscar	English	M	Kyutai tts-voices	CC0
sophie	English	F	Kyutai tts-voices	CC0
carmen	Spanish	F	CML-TTS	CC-BY-4.0
dave	Spanish	M	OHF-Voice donations	CC0
colette	French	F	Kyutai tts-voices	CC-BY-4.0
henri	French	M	Kyutai tts-voices	CC-BY-4.0
kerstin	German	F	OHF-Voice donations	CC0
thorsten	German	M	Thorsten-Voice	CC0
dante	Italian	M	MLS	CC-BY-4.0
paola	Italian	F	OHF-Voice donations	CC0
darkman	Polish	M	OHF-Voice donations	CC0
gosia	Polish	F	OHF-Voice donations	CC0
tugao	Portuguese (European)	M	OHF-Voice donations	CC0
nathalie	Dutch	F	OHF-Voice donations	CC0
pim	Dutch	M	OHF-Voice donations	CC0
nils	Swedish	M	NST Swedish	CC0
selma	Swedish	F	NST Swedish	CC0
freja	Danish	F	NST Danish	CC0
soren	Danish	M	NST Danish	CC0
ines	Portuguese (Brazilian)	F	CML-TTS	CC-BY-4.0

All 28 voices are included in both loudr-1 and loudr-1-turbo and load by name:

voice = engine.voice("henry")

The gallery compares the 10 English voices on the same story, with seed 7 and matched loudness.

Enrol your own

Ten seconds of clean audio is enough:

import loudkit as lk

mine = lk.enroll("my-recording.wav", "loudreader/loudr-1", name="my-voice")
mine.save("voices/my-voice.safetensors")

Consent is yours to obtain. See RESPONSIBLE_USE.md.