Model reference · open weights

Qwen3-TTS-Tokenizer-12Hz

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.

Audio Qwen 1 variants 122k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What Qwen3-TTS-Tokenizer-12Hz is

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

What it is

MakerQwen
TypeAudio & music
Parameters (lead)171M
Variants1
Released2026-01-21
Popularity122k downloads / month
Likes78
LicenceOpen weights

How it works

How audio & music work

Audio or textinputAudio modelrecognise / synthesiseText or audiooutputSpeech-to-text turns audio into text; text-to-speech and music models turn text into audio.

Variants

Sizes & precisions

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.

VariantParamsPrecisionVRAMFits 16 GBWeights
Qwen3-TTS-Tokenizer-12Hz171MBF16~0.4 GBWeights ↗

Using it via the API

Call it like any OpenAI endpoint

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

Details

Languages, data & research

Tags

safetensors qwen3_tts_tokenizer_12hz audio tts speech codec audio-to-audio

Papers

Licence

Open weights

Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want Qwen3-TTS-Tokenizer-12Hz on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More audio & music

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms