Skip to content
Local AI Wizard
Your machine
Theme

Magpie-Multilingual 357M

NVIDIA · nvidia/magpie_tts_multilingual_357m

Weights license: Publisher terms: NVIDIA Open Model License · code and components may use other terms

Reported by the publisher26 resultsNVIDIA's model card · read 2026-10-26 · not ranked · see them
Published repository size2 GBAll published files · not runtime memory
Parameters0.36 Bmanufacturer model card
Published components1Listed in the model card

Quality

No comparable score

Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. Leaderboard (link only)

Reported by the publisher

26 results · NVIDIA's model card · read 2026-10-26
Arabic (ar)
1.62%CER↓ (%) · v2607
Chinese (zh)
3.17%CER↓ (%) · v2607
English (en)
0.37%CER↓ (%) · v2607
English accented (en)
0.34%CER↓ (%) · v2607
French (fr)
1.54%CER↓ (%) · v2607
German (de)
0.80%CER↓ (%) · v2607
Hindi (hi)
1.23%CER↓ (%) · v2607
Italian (it)
2.19%CER↓ (%) · v2607
Every reported result26
Japanese (ja)
1.40%CER↓ (%) · v2607
Korean (ko)
2.69%CER↓ (%) · v2607
Portuguese (pt)
2.91%CER↓ (%) · v2607
Spanish (es)
0.60%CER↓ (%) · v2607
Vietnamese (vi)
0.59%CER↓ (%) · v2607
Arabic (ar)
0.806SSIM↑ (pred-context) · v2607
Chinese (zh)
0.833SSIM↑ (pred-context) · v2607
English (en)
0.822SSIM↑ (pred-context) · v2607
English accented (en)
0.746SSIM↑ (pred-context) · v2607
French (fr)
0.747SSIM↑ (pred-context) · v2607
German (de)
0.742SSIM↑ (pred-context) · v2607
Hindi (hi)
0.788SSIM↑ (pred-context) · v2607
Italian (it)
0.773SSIM↑ (pred-context) · v2607
Japanese (ja)
0.775SSIM↑ (pred-context) · v2607
Korean (ko)
0.807SSIM↑ (pred-context) · v2607
Portuguese (pt)
0.753SSIM↑ (pred-context) · v2607
Spanish (es)
0.793SSIM↑ (pred-context) · v2607
Vietnamese (vi)
0.725SSIM↑ (pred-context) · v2607

Values as printed on the card, with the publisher's own settings (card section: Evaluation). Not comparable across publishers and not used in any ranking. Model card

Runs on

Enough memory for the estimate 119

The 16-bit planning estimate fits this memory. It is not a reviewed minimum.

Show all 119

The publisher documents no minimum for this checkpoint (sources checked 2026-10-13). Hardware profiles are grouped by a labelled 16-bit planning estimate from the published parameter count (2 bytes per parameter, 20% allowance, 2 GB reserve). Precision, resolution, duration, text encoders and offload change the real requirement. Not a measured run.

Plan memory for this model

Consider it for

Consider Magpie-Multilingual 357M from NVIDIA for the text-to-speech task (0.36B parameters).

Check first

This catalog has not verified hardware requirements for this entry. Actual memory depends on precision, resolution, duration and offload; consult the official source.

Measured speed

No published measurement for this checkpoint

Speed (real-time factor, or seconds per clip) is shown only when a source publishes it with hardware, build and setup. It is never estimated.

How to run

Hardware requirement not reviewed. This catalog has not verified hardware requirements for this entry. Actual memory depends on precision, resolution, duration and offload; consult the official source.

Documented ways to run it

Copied as printed in the linked source (read 2026-10-18); not run by this site.

NeMo · model card · Run MagpieTTS locally with NeMo-Speech.cpp
nemo-speech synthesize "Hello from Magpie Multilingual." \
  --output speech.wav
Setup stated first by the source · NeMo
pip install nemo_toolkit[tts]@main
pip install kaldialign
NeMo · model card · Method 1 — Single utterance inference
from nemo.collections.tts.models import MagpieTTSModel

speaker_map = {
    "Aria": 0,
    "Jason": 1,
    "John": 2,
    "Leo": 3,
    "Sofia": 4,
}
transcript = "Hello world from NeMo Text to Speech."
language = "en"
speaker = "Sofia"
speaker_idx = speaker_map[speaker]

# Load the latest checkpoint (from the `main` branch).
model = MagpieTTSModel.from_pretrained("nvidia/magpie_tts_multilingual_357m")
audio, audio_len = model.do_tts(transcript, language=language, apply_TN=False, speaker_index=speaker_idx)

# To apply custom phoneme customization in supported languages like English
# Surround the IPA string in a '|' character and add a space token between each IPA character.
ipa_transcript = "Hello world from | ˈ n ɛ m o ʊ | Text to Speech."
audio, audio_len = model.do_tts(ipa_transcript, language=language, apply_TN=False, speaker_index=speaker_idx)

Evidence level: Generic estimate only; no execution reproduced by this site.

Before downloading
  1. Check the exact checkpoint and license linked here.
  2. Confirm a compatible runtime and precision or quantization for your platform.
  3. Allow for context, batch size and any extra media components beyond the weights.

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Task and modality
text-to-speech · audio
Count and basis
0.36B · manufacturer model card
Released
nvidia/magpie_tts_multilingual_357m model card · read 2026-10-13source
Published repository size
2 GBNot runtime memory or a minimum download.files
Published components
Technical details pending review
Runtime and precision
No local execution verified.
Commercial use
Allowed NVIDIA Open Model License Agreement, last modified 2025-10-24 (copy shipped in NVIDIA's NVlabs/GRAIL repository) · read 2026-10-18license text

License, parameter count and release date come from the publisher's sources listed on this page (a date no source states is left empty). The hardware requirement has not been reviewed, so memory is a labelled estimate. The repository size, when shown, is the full published download.

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Catalog reviewed: 2026-09-22.