Marketplace · Text-to-speech

Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice

Call Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice through one OpenAI-compatible API. It's served by 1 host on the Inpherio grid, each at a price it sets — your request goes to the cheapest healthy one, and fails over to the next if it's down.

From
£0.41
per hour of audio
£1 buys about 2.4 hours of audio
Hosts
1
Loaded now
0

At a glance.

multilingual

  • Type: Text-to-speech
  • Hosts serving it now: 1 (0 with it loaded in memory)
  • Engines: vllm
  • Rentable: a whole host from £0.60 an hour (rentals)
python · openai sdk
from openai import OpenAI
client = OpenAI(base_url="https://inpherio.co.uk/v1",
                api_key=INPHERIO_API_KEY)
audio = client.audio.speech.create(
    model="Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice",
    input="Hello from the grid.",
)

Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice in detail.

[Qwen3-TTS](https://github.com/QwenLM/Qwen3-TTS) is a series of advanced multilingual, controllable, robust, and streaming text-to-speech models developed by the Qwen team.

Published by
Qwen
Parameters
906M
Architecture
qwen3_tts
Licence
Apache 2.0
Task
text to speech
Languages
zh, en, ja, ko, de, fr, ru, pt, es, it
First published
21 Jan 2026
Last updated
29 Jan 2026
Downloads (30 days)
738,217 on Hugging Face
Likes
211

qwen3_tts tts qwen audio text-to-speech zh en ja ko de fr ru pt es it

The model card

Published by the model's authors on Hugging Face — shown as they wrote it, unedited by Inpherio.

Qwen3-TTS-12Hz-0.6B-CustomVoice

Qwen3-TTS is a series of advanced multilingual, controllable, robust, and streaming text-to-speech models developed by the Qwen team.

This specific checkpoint is the 0.6B CustomVoice variant, based on the 12Hz tokenizer. It supports 9 premium timbres and allows for fine-grained style control over target voices via natural language instructions across 10 major languages.

Key Features

  • Multilingual Synthesis: Supports Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian.
  • Intelligent Control: Adapts tone, rhythm, and emotional expression based on natural language instructions (e.g., "Speak in a very happy tone").
  • Low Latency: Optimized for streaming generation with the Qwen3-TTS-Tokenizer-12Hz, achieving end-to-end synthesis latency as low as 97ms.

Quickstart

To use Qwen3-TTS, you can install the qwen-tts package:

pip install -U qwen-tts

Sample Usage

import torch
import soundfile as sf
from qwen_tts import Qwen3TTSModel

### Load the model
model = Qwen3TTSModel.from_pretrained(
    "Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice",
    device_map="cuda:0",
    dtype=torch.bfloat16,
    attn_implementation="flash_attention_2",
)

### Generate speech with specific instructions
wavs, sr = model.generate_custom_voice(
    text="其实我真的有发现,我是一个特别善于观察别人情绪的人。",
    language="Chinese", 
    speaker="Vivian",
    instruct="用特别愤怒的语气说", 
)

### Save the generated audio
sf.write("output_custom_voice.wav", wavs[0], sr)

Supported Speakers

For Qwen3-TTS-12Hz-0.6B-CustomVoice, the following speakers are supported. We recommend using each speaker’s native language for the best results:

SpeakerVoice DescriptionNative Language
VivianBright young female voice.Chinese
SerenaWarm, gentle young female voice.Chinese
Uncle_FuSeasoned male voice, mellow timbre.Chinese
DylanYouthful Beijing male voice.Chinese (Beijing)
EricLively Chengdu male voice.Chinese (Sichuan)
RyanDynamic male voice with rhythm.English
AidenSunny American male voice.English
Ono_AnnaPlayful Japanese female voice.Japanese
SoheeWarm Korean female voice.Korean

Citation

If you find Qwen3-TTS useful for your research, please consider citing:

@article{Qwen3-TTS,
  title={Qwen3-TTS Technical Report},
  author={Hangrui Hu and Xinfa Zhu and Ting He and Dake Guo and Bin Zhang and Xiong Wang and Zhifang Guo and Ziyue Jiang and Hongkun Hao and Zishan Guo and Xinyu Zhang and Pei Zhang and Baosong Yang and Jin Xu and Jingren Zhou and Junyang Lin},
  journal={arXiv preprint arXiv:2601.15621},
  year={2026}
}

Sources: Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice on Hugging Face. Collected from public sources on 8 Nov 2026; the host serving it may run a different build or quantisation — the marketplace shows each host's own measurements.

Who's serving it.

Every host benchmarked this model on its own hardware before serving it. Prices are set by each host; health is scored by the platform from what it observes.

Hosts serving Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice right now
HostTierPriceMeasured speedHealthStateRent
GTX 1080 Ti (11G)L1£0.41 /h audio2 chars/s78loads on request£0.60/h

Live data, refreshed on every visit. How billing works.

Room on the grid for your machine.

Right now one machine serves Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice. If it drops, so does every request for it — a second host is what turns it into failover, and the grid needs that more than another copy. The router weighs price, measured speed, health and whether the model is already loaded — so a host with a sharper price or quicker hardware wins the next call.

Hosts now
1
0 loaded in memory
Price to beat
£0.41
per hour of audio

Set your own price — you keep 85% of what it earns, and new hosts start with 12 months fee-free (up to £250 of earnings). A payout fee of £2 + 1% per payout to a UK bank account, £2 + 2% to any other country applies when you're paid. Install the connector, load Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice, and the platform benchmarks it on your hardware before your first request.