Downloads · 30 days
0
runanywhere/magpie_tts_357m_HNPU
magpie_tts_357m_HNPU is a text-to-speech model from runanywhere. Use it when you need text read aloud. It is set up for qhexrt. The card lists the license as other.
Prebuilt QHexRT bundle of nvidia/magpiettsmultilingual357m for the Qualcomm Hexagon NPU. Text in, 22.05 kHz mono speech out, running on-device.
Downloads · 30 days
0
Access
Public
Updated Jul 26, 2026
Repo size
1.5 GB
Likes
0
Public
Click a slice to open those files.
.bin1.5 GB · 100%
From the Hugging Face model README
Prebuilt QHexRT bundle of
nvidia/magpie_tts_multilingual_357m for the
Qualcomm Hexagon NPU. Text in, 22.05 kHz mono speech out, running on-device.
For the model itself — architecture, languages, voices, intended use, and limitations — see the upstream model card. This repository adds only the on-device artifacts.
| directory | Hexagon architecture |
|---|---|
v75/ | Hexagon v75 |
v81/ | Hexagon v81 |
Each directory is a self-contained bundle. Bundles are architecture-specific: use the directory matching your device.
Governed by the NVIDIA Open Model License,
inherited from the upstream model. The audio codec component derives from
nvidia/nemo-nano-codec-22khz-1.89kbps-21.5fps.