---
license: apache-2.0
library_name: transformers
pipeline_tag: text-to-speech
language:
- en
- zh
base_model:
- Qwen/Qwen3-TTS-12Hz-0.6B-Base
base_model_relation: finetune
tags:
- zen3
- zen3-tts
- zenlm
- qwen3-tts
- speech-synthesis
- edge
- low-latency
- 12hz
---

# Zen3 TTS 0.6B

Compact ~0.6B Zen3 text-to-speech model at 12 Hz, sized for edge and latency-sensitive synthesis.

Derived by fine-tuning [`Qwen/Qwen3-TTS-12Hz-0.6B-Base`](https://huggingface.co/Qwen/Qwen3-TTS-12Hz-0.6B-Base) (Alibaba Cloud, Apache-2.0).

- Architecture: `Qwen3TTSForConditionalGeneration` (`qwen3_tts`)
- Parameters: ~0.6B
- Base model: [`Qwen/Qwen3-TTS-12Hz-0.6B-Base`](https://huggingface.co/Qwen/Qwen3-TTS-12Hz-0.6B-Base)

## Weights

This repository contains the model weights: `model.safetensors` (talker) plus a `speech_tokenizer/` module (12 Hz codec), config and tokenizer files.

The model uses the `qwen3_tts` architecture and loads with `transformers` (>= 4.57). It is API-compatible with the upstream base — follow the inference recipe on the base model card [`Qwen/Qwen3-TTS-12Hz-0.6B-Base`](https://huggingface.co/Qwen/Qwen3-TTS-12Hz-0.6B-Base).

## Provenance

Fine-tuned from [`Qwen/Qwen3-TTS-12Hz-0.6B-Base`](https://huggingface.co/Qwen/Qwen3-TTS-12Hz-0.6B-Base) (Apache-2.0). See `NOTICE` for full attribution.