Model reference · open weights
Qwen3-TTS-12Hz 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-12Hz-0.6B-Base Qwen3-TTS Technical Report | GitHub Repository | Hugging Face Demo Qwen3-TTS is a family of advanced multilingual, controllable, robust, and streaming text-to-speech models. Trained on over 5 million hours of speech data spanning 10 languages, Qwen3-TTS supports state-of-the-art 3-second voice cloning and description-based control. This specific checkpoint is the 0.6B Base model, which is capable of rapid voice cloning from a user-provided audio input. Quickstart Installation Sample Usage (Voice Clone) To clone a voice and synthesize new content using the Base model, you can use the following code snippet: Overview Introduction Qwen3-TTS covers 10 major languages (Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian) as well as multiple dialectal voice profiles to meet global application needs. 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, it realizes full-information end-to-end speech modeling. Extreme Low-Latency Streaming Generation: End-to-end synthesis latency as low as 97ms, meeting the rigorous demands of real-time interactive scenarios. Intelligent Text Understanding and Voice Control: Supports speech generation driven by natural language instructions, allowing for flexible control over multi-dimensional acoustic attributes. Model Architecture Citation If you find this work useful, please consider citing the technical report:
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | Qwen |
|---|---|
| Type | Audio & music |
| Parameters (lead) | 915M |
| Variants | 1 |
| Released | 2026-01-21 |
| Popularity | 533k downloads / month |
| Likes | 285 |
| 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-0.6B-Base | 915M | BF16 | ~2.1 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys qwen3-tts-12hz for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (qwen3-tts-12hz 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" -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 ↗