On-device voice input: voice isolation, voice activity, wake words, voiceprints, text to phonemes. Apache-2.0, under 8 MB for all five.
AI & ML interests
None defined yet.
Recent Activity
View all activity
Organization Card
Small models for voice agents that run on the device: in the browser (WebAssembly), in Python and on Android, with plugins for LiveKit Agents and Pipecat. No server, no key. Code and weights under Apache-2.0. Early preview (0.x).
| Model | What it does | Size |
|---|---|---|
| Focus | Keeps the closest voice, or one person's voice from their print, and removes noise, music and other voices | 1.1 MB |
| Cue | Tells when someone speaks, every 30 ms | 1.1 MB |
| Spot | Hears any word you type, in 7 languages, with no training | 2.8 MB |
| Lex | Turns a written word into its likely pronunciations | 1.8 MB |
| Timbre | Makes voiceprints and compares them | 0.74 MB |
models 5
alkove-ai/alkove-lex-1-preview
Other • Updated
alkove-ai/alkove-timbre-1-preview
Audio Classification • Updated
alkove-ai/alkove-spot-1-preview
Audio Classification • Updated
alkove-ai/alkove-cue-1-preview
Voice Activity Detection • Updated • 1
alkove-ai/alkove-focus-1-preview
Audio-to-Audio • Updated
datasets 0
None public yet