---
license: apache-2.0
pipeline_tag: text-to-speech
tags: [text-to-speech, voice-cloning, voice-design]
---

# VoxCPM2 (TinyPine mirror)

**VoxCPM2** by [OpenBMB](https://github.com/OpenBMB/VoxCPM), unmodified, mirrored so TinyPine Studio's
installer does not depend on third-party download links. TinyPine did not train or change the model.
Upstream: [openbmb/VoxCPM2](https://huggingface.co/openbmb/VoxCPM2). Licence: Apache License 2.0 (`LICENSE`).

Also included: the AudioSeal watermark generator and detector (Meta, MIT, `audioseal/LICENSE`), which
TinyPine embeds in every clip it makes, from [facebook/audioseal](https://huggingface.co/facebook/audioseal).

SHA-256 of the large files:
- `audiovae.pth` 94b5d51e107e0507d4acc976cfdadb64edd6fd06d1f751dadbf2fd1594274bf1
- `model.safetensors` f7f964cfa9da23653baec6e6f7750719977ad944ed9f95fe52fe3a620506891d
- `audioseal/generator_base.pth` 7a845b5fbe9364a63a3909d8ab3fe064d13a76ae4c2e983573e08c69b7b51748
- `audioseal/detector_base.pth` 8a78e8a83584113523e161fc599fcab10fd0e94c04d2eb9d2fa1e9ec91ab69d9