Sovereign speech technology
Language tools that stay with the community that owns the language.
KinSpeak builds speech recognition, natural voices, and classroom tools for Indigenous language revitalisation. Everything runs on local hardware. No cloud services, no third parties, no data leaving community control.
🎙️
Listen
Speech recognition built for languages with small archives, turning community recordings into searchable, written language.
🔊
Speak
Natural synthetic voices, created only under documented speaker consent, enforced in code, not just in policy.
📖
Teach
Lesson builders, talking books, and pronunciation practice generated only from vocabulary verified against published grammars and speakers.
Built first for a first language community in northern Australia, and designed so
the whole platform can be stood up for any language. Language data and models are
community attributed and built to transfer to the community outright, on the
community's decision. Every word served can be traced
to a published grammar or a speaker recording, and words that cannot be verified are
reported honestly, never guessed.
Working on a language?
Demonstrations by invitation. Happy to talk to language centres, schools,
and communities anywhere.
rod@kinspeak.org