Model reference · open weights
Qwen3-TTS-12Hz-VoiceDesign is an open-weight audio or speech model from Qwen, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
Qwen3-TTS   🤗 <a href="https://huggingface.co/collections/Qwen/qwen3-tts"Hugging Face</a   |   🤖 <a href="https://modelscope.cn/collections/Qwen/Qwen3-TTS"ModelScope</a   |   📑 <a href="https://qwen.ai/blog?id=qwen3tts-0115"Blog</a   |   📑 <a href="https://huggingface.co/papers/2601.15621"Paper</a   |   💻 <a href="https://github.com/QwenLM/Qwen3-TTS"GitHub</a We release Qwen3-TTS, a series of powerful speech generation models developed by Qwen, offering comprehensive support for voice cloning, voice design, ultra-high-quality human-like speech generation, and natural language-based voice control. Overview Qwen3-TTS covers 10 major languages (Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian) as well as multiple dialectal voice profiles. Key features: Powerful Speech Representation: Powered by the self-developed Qwen3-TTS-Tokenizer-12Hz, it achieves efficient acoustic compression and high-dimensional semantic modeling. Universal End-to-End Architecture: Utilizing a discrete multi-codebook LM architecture to bypass traditional information bottlenecks. Extreme Low-Latency Streaming Generation: Supports streaming generation with end-to-end synthesis latency as low as 97ms. Intelligent Voice Control: Supports speech generation driven by natural language instructions for flexible control over timbre, emotion, and prosody. Quickstart Environment Setup Install the qwen-tts Python package from PyPI: Python Package Usage Evaluation Zero-shot speech generation on the Seed-TTS test set (Word Error Rate (WER, ↓)): Citation If you find our paper and code useful in your research, please consider giving a star ⭐ and citation 📝:
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | Qwen |
|---|---|
| Type | Audio & music |
| Parameters (lead) | 1.9B |
| Variants | 1 |
| Runs with | qwen-tts |
| Released | 2026-01-21 |
| Popularity | 285k downloads / month |
| Likes | 398 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| Qwen3-TTS-12Hz-1.7B-VoiceDesign | 1.9B | BF16 | ~4.4 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys qwen3-tts-12hz-voicedesign for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (qwen3-tts-12hz-voicedesign below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="qwen3-tts-12hz-voicedesign" -F file=@audio.mp3
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗