Downloads · 30 days
16
11% of all-time downloads
phoonnx-magpie-tts
OpenVoiceOS/phoonnx-magpie-tts
phoonnx-magpie-tts is a text-to-speech model from OpenVoiceOS. Use it when you need text read aloud. It is set up for phoonnx. The card lists the license as other.
ONNX export of nvidia/magpiettsmultilingual357m (MagpieTTS Multilingual, v2607) for use with phoonnx.
All-time downloads
145
Public
Repo size
2.6 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.onnx_data1.5 GB · 98%
At a glance
- Task
- Text-to-Speech
- Library
- phoonnx
- License
- other
- Model type
- magpie-tts
- Access
- Public
- Created
- Aug 4, 2026
- Updated
- Aug 4, 2026
- SHA
- 24d2157c
Base models
Model card
From the Hugging Face model README
phoonnx-magpie-tts
ONNX export of nvidia/magpie_tts_multilingual_357m (MagpieTTS Multilingual, v2607) for use with phoonnx.
The original model is a transformer encoder-decoder that predicts discrete audio codec tokens autoregressively. It uses 8 codebooks, a frame stacking factor of 2, and a local transformer that refines each stacked frame. A frozen NanoCodec decodes the tokens into a 22.05 kHz waveform.
Weights and architecture are NVIDIA's. This repository only changes the file format.
License and attribution
The model is released under the NVIDIA Open Model License. That license applies to every file here. Developed by NVIDIA. See the original model card for the full model card, dataset list, and limitations.
Contents
| File | Purpose |
|---|---|
text_encoder.onnx | 6-layer causal text encoder. Text token ids to encoder states. |
cross_kv.onnx | Per-layer cross-attention K/V, computed once from the encoder states. |
decoder_step.onnx | 12-layer causal decoder with external KV cache. Returns codebook logits, decoder states, the updated cache, and per-layer cross-attention probabilities. |
local_step.onnx | One step of the 2-layer local transformer that refines the 16 stacked codebook tokens. |
audio_embed.onnx | Stacked codebook tokens to one decoder input embedding. |
lt_embed.onnx | One codebook token to the next local-transformer input. |
codec_decoder.onnx | NanoCodec decoder. Codes to waveform. |
assets/context_embeddings.npy | Baked speaker context embeddings, shape (5, 217, 768). |
assets/tokenizer.json | Aggregated tokenizer vocabulary and per-language offsets. |
assets/tokenizer/ | IPA dictionaries and heteronym lists shipped inside the original checkpoint. |
config.json | Graph inventory and IO contract. |
All graphs are opset 18 and use external data files (*.onnx.data). Download the whole
repository, not single files.
Two decode modes
NeMo ships use_kv_cache_for_inference: false. In that mode the newest attention prior is
re-applied over the whole history, so the decoder states must be recomputed every step. A
KV-cached decoder does not produce the same tokens.
decoder_step.onnx supports both:
- exact - pass the full sequence with an empty cache every step. Matches the NeMo default.
- cached - pass one frame plus the cache. Matches NeMo with
use_kv_cache_for_inference: true. Roughly 2.5x faster.
Both reach 100% greedy token agreement with the matching NeMo reference across all 8 codebooks.
Usage
from phoonnx.model_manager import TTSModelManager
manager = TTSModelManager()
voice = manager.get_voice(magpie/Leo/en)
wav = voice.synthesize(Hello from Magpie running on ONNX.)
Related
- phoonnx - the ONNX TTS runtime that consumes this repository
- nvidia/magpie_tts_multilingual_357m - the source checkpoint
- nvidia/nemo-nano-codec-22khz-1.89kbps-21.5fps - the codec
- Task
- Text-to-Speech
- Library
- phoonnx
- Type
- magpie-tts
- License
- other
- Languages
- ar, de, en, es, fr, hi
- Created
- Aug 4, 2026
- Updated
- Aug 4, 2026