Model reference · open weights

Qwen3-TTS

Qwen3-TTS is an open-weight audio or speech model from Serveurperso, 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 Serveurperso 1 variants 901k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What Qwen3-TTS is

Qwen3-TTS GGUF GGUF weights for qwentts.cpp, a C++17/GGML port of Qwen3-TTS 12 Hz (Qwen team, Alibaba). Multilingual zero shot TTS with named speakers and Mandarin dialects, 24 kHz mono. Runs on CPU, CUDA, Metal, Vulkan. Files Two GGUFs load together : qwen-talker-{size}-{mode}-{variant}.gguf Qwen3 LM + code predictor MTP head + optional speaker encoder, text - 12 Hz codes qwen-tokenizer-12hz-{variant}.gguf SEANet + ConvNeXt + DAC v2 + RVQ, 12 Hz codes <- 24 kHz audio Three modes are available across two talker sizes : The tokenizer is shared across every talker. Quick start Backends Set GGMLBACKEND to force a device, otherwise the runtime picks the best one available. Quantization policy Tokenizer GGUFs are not uniform quants. Three categories get a dedicated treatment : Conv kernel rows (K=7,3,1) never divide a K-quant block size, so the quantizer skips the Q intermediates and lands on F16 directly. This is the last resort branch of llama.cpp's tensortypefallback applied unconditionally for these kernels. F16 has no block size and matches the runtime target dtype on every backend. The talker LM (Qwen3 backbone, hidden divisible by 256) follows standard llama.cpp K-quant across variants. The code predictor MTP head and the speaker encoder live in the talker GGUF and share its quantization. License Upstream model : Qwen3-TTS by Alibaba / Qwen team, Apache 2.0 Audio codec : Qwen3-TTS-Tokenizer-12Hz (Qwen team), Apache 2.0 GGUF tooling : qwentts.cpp, MIT

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

MakerServeurperso
TypeAudio & music
Variants1
Runs withgguf
Based onQwen/Qwen3-TTS-Tokenizer-12Hz, Qwen/Qwen3-TTS-12Hz-0.6B-Base
Released2026-05-11
Popularity901k downloads / month
Likes37
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-GGUFGGUFWeights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys qwen3-tts for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (qwen3-tts 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" -F file=@audio.mp3

Details

Languages, data & research

Languages

zh en fr de es it pt ja ko ru ar

Tags

gguf tts text-to-speech voice-cloning voice-design mandarin-dialects ggml qwen qwen3 qwen3-tts cpp zh en fr

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 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