Model reference · open weights
Qwen3-TTS-Tokenizer-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-Tokenizer-12Hz This repository contains the Qwen3-TTS-Tokenizer-12Hz, as presented in the paper Qwen3-TTS Technical Report. Qwen3-TTS-Tokenizer-12Hz achieves extreme bitrate reduction and ultra-low-latency streaming, enabling immediate first-packet emission through its 12.5 Hz, 16-layer multi-codebook design and a lightweight causal ConvNet. Paper: Qwen3-TTS Technical Report GitHub Repository: QwenLM/Qwen3-TTS Demo: Hugging Face Space Quickstart Environment Setup Install the qwen-tts Python package from PyPI: Tokenizer Encode and Decode You can encode audio into discrete tokens for storage or transport and decode them back into speech using the snippet below: 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. Key features: Powerful Speech Representation: Powered by the self-developed Qwen3-TTS-Tokenizer-12Hz, it achieves efficient acoustic compression and high-dimensional semantic modeling of speech signals. It fully preserves paralinguistic information and acoustic environmental features. Extreme Low-Latency Streaming Generation: Based on the innovative Dual-Track hybrid streaming generation architecture, it can output the first audio packet immediately after a single character is input, with end-to-end synthesis latency as low as 97ms. Model Architecture Released Tokenizers Evaluation For detailed evaluation results on speech generation consistency, speaker similarity, and tokenizer benchmarks (ASR tasks, PESQ, STOI, UTMOS), please refer to the technical report or the GitHub repository. Citation
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | Qwen |
|---|---|
| Type | Audio & music |
| Parameters (lead) | 171M |
| Variants | 1 |
| Released | 2026-01-21 |
| Popularity | 122k downloads / month |
| Likes | 78 |
| 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-Tokenizer-12Hz | 171M | BF16 | ~0.4 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys qwen3-tts-tokenizer-12hz for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (qwen3-tts-tokenizer-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-tokenizer-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 ↗