moonbox-dev/Qwen3-TTS-12Hz-1.7B-Base-ONNX

text-to-speech model by moonbox-dev

Open original source ↗

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

ONNX builds of Qwen3-TTS 1.7B, made by Moonbox for on-device use with ONNX Runtime (CPU, CUDA, DirectML). Each precision is one folder holding the graphs and a small Python pipeline.py that does the rest (features, prompt, sampling loop); what the graphs take and return is under How to run. The last column is the benchmark on Moonbox's TTS set (voice cloning of English and Chinese sentences from a LibriSpeech and an AISHELL-1 prompt; details under How to run): error rate of a Whisper transcript against the text, speaker similarity to the prompt and DNSMOS, against the original PyTorch model. Qwen3-TTS 12Hz 1.7B Base (Qwen's speech generator: voice cloning from a few seconds of reference audio and its transcript, 10 languages, 24 kHz output) as eight ONNX graphs plus pipeline.py, a numpy runtime that reproduces qwen-tts 0.1.1's Qwen3TTSModel.generatevoiceclone around them: [1, S, 2048], attentionmask, pastkeyvalues.{0..27}.key / .value [1, 8, past, 128]…

moonbox-dev/Qwen3-TTS-12Hz-1.7B-Base-ONNX on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-11-18T08:04:33.994Z

Inside the original model card — Document outline
  1. Qwen3-TTS 1.7B ONNX
  2. Files
  3. How to run
  4. How these were made
  5. License
  6. Original model card
  7. Qwen3-TTS
  8. Overview
  9. Introduction
  10. Model Architecture
  11. Released Models Description and Download
  12. Quickstart

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Links from the model card

References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.

Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

moonbox-dev/Qwen3-TTS-12Hz-1.7B-Base-ONNX is a text-to-speech model repository published by moonbox-dev on Hugging Face. The source reports the onnx library.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task
text-to-speech
Library
onnx
Recent downloads (30 days)
0
Cumulative likes
0
Hugging Face trending score
0
Reported safetensors parameters
Not reported
Architecture
Not reported
License
apache-2.0
Access
Not gated by Hugging Face
Created
2026-11-18T06:28:04.000Z
Last modified
2026-11-18T06:30:37.000Z

Compatibility and lineage

Language coverage was not reported.

Reported base models: Qwen/Qwen3-TTS-12Hz-1.7B-Base

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-11-18T07:01:26.893Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related models

hexgrad/Kokoro-82M

audio-cpp/audio.cpp-gguf

coqui/XTTS-v2

k2-fsa/OmniVoice

ResembleAI/chatterbox

pnnbao-ump/VieNeu-TTS-v3-Turbo