Cloning a voice at 48 kHz with VoxCPM2 in ElevenLabs API quality
The VoxCPM2 model from Soniqo enables voice cloning at 48 kHz quality directly on user devices. This technology allows for various applications, including personal audiobook narration and multilingual content creation. It offers advantages such as privacy, offline use, and no per-call costs compared to cloud-based alternatives like ElevenLabs.
- ▪VoxCPM2 runs locally on devices, providing studio-quality audio without needing internet access.
- ▪Users can clone voices from short audio clips or create new voices based on text descriptions.
- ▪The model supports multiple languages and can preserve accents during voice cloning.
Opening excerpt (first ~120 words) tap to expand
Blog·Voice cloningMay 17, 2026Cloning a voice at 48 kHzwith VoxCPM2.A new TTS model just landed in Soniqo. It runs on your laptop, outputs studio-quality 48 kHz audio, and clones a voice from a single short clip. This post walks through what you can build with it, the three ways it lets you clone a voice, and a friendly look at how the model works inside.What you can buildFour things that change when cloning runs locally.Running cloning on the device unlocks four properties at once — privacy, offline use, no per-call cost, and full voice ownership. Each of these opens a class of product that's awkward to build any other way.Personal audiobook narratorsRecord 30 seconds of a parent reading.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Soniqo.
Discussion
0 commentsMore from Soniqo
