Skip to content
HostYourAI
03 Model garden Serve

Qwen3 TTS 12Hz 0.6B CustomVoice

Runs as your own dedicated GPU deployment, ready to launch from the wizard. Data stays in Europe.

Get started ← All models
curl 
$ curl https://hostyourai.com/api/v1/audio/speech \
  -H "Authorization: Bearer hyai-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice",
    "input": "Hello!"
  }' --output speech.mp3

Call it now

Drop-in replacement for OpenAI: change only the base URL and API key. The Anthropic format (/v1/messages) is supported too.

Serve Model garden On request
Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice

text->speech · Qwen · sovereign EU

Runs on EU infrastructure operated by European companies, from your request to the GPU. See the full chain

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.

Router
Router · on request
Dedicated
Dedicated · available
0.9BParameters
8GBMinimum VRAM
POST /api/v1/audio/speech On request

Specifications

Parameters0.9B
Minimum VRAM8 GB
ArchitectureQwen3TTSForConditionalGeneration (vLLM)
Licenseapache-2.0
Modalitytext->speech
ReleasedJanuary 2026
PublisherQwen ↗

Pricing

Shared router · per token

On request Not available on the shared router. Pricing on request as a dedicated GPU deployment.

Dedicated GPU · per hour

from €2,03 per hourYour own vLLM instance on European cloud (8 GB VRAM), billed per minute.

Shared EU router, you pay only per token. Dedicated GPU deployments are billed per minute, see pricing.

Questions

Frequently asked questions

Can I run Qwen3 TTS 12Hz 0.6B CustomVoice in the EU?

Yes. HostYourAI runs Qwen3 TTS 12Hz 0.6B CustomVoice on GPUs in European datacenters via vLLM. Prompts and outputs never leave the EU and there is no US cloud provider in the chain.

Is hosting Qwen3 TTS 12Hz 0.6B CustomVoice GDPR-compliant?

Yes. All processing happens inside the EU, a Data Processing Agreement (DPA) is available and the subprocessor list is public. Open-source weights also mean: no training on your data.

How much does Qwen3 TTS 12Hz 0.6B CustomVoice cost?

Qwen3 TTS 12Hz 0.6B CustomVoice needs several GPUs at once, so it runs as a dedicated deployment billed per GPU minute rather than per token. Tell us your volume and we will work it out with you.

Is the API OpenAI-compatible?

Yes. You use the standard OpenAI SDKs with a custom base URL (https://hostyourai.com/api/v1). The Anthropic Messages API is supported as a drop-in as well.

More models from Qwen

Qwen Image 2.1 Turbo

 7.1B

Qwen-Image-2.1-Turbo is an accelerated checkpoint of Qwen-Image-2.1 for text-to-image generation and image editing with 8 denoising steps. It uses the same 7B visual generation architecture and loads directly with QwenImage21Pipeline in Diffusers.

View model →

Qwen Image 2.1 PE T2I

 9.4B 262K context

We are excited to open-source Qwen-Image-2.1, a unified text-to-image generation and image editing model in the Qwen family. With just 7B parameters in its visual generation component (32 Single-Stream DiT layers), Qwen-Image-2.1 balances generation quality, inference efficiency, and versatility.

View model →

Qwen Image 2.1

 7.1B

We are excited to open-source Qwen-Image-2.1, a unified text-to-image generation and image editing model in the Qwen family. With just 7B parameters in its visual generation component (32 Single-Stream DiT layers), Qwen-Image-2.1 balances generation quality, inference efficiency, and versatility.

View model →

Qwen3.8 Flash Next

 180B 262K context

[!Note] This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, TokenSpeed, etc.

View model →

Qwen3.8 27B

 28B 262K context

[!Note] This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, TokenSpeed, etc.

View model →

Qwen3 ASR 0.6B hf

 0.8B 66K context

The Qwen3-ASR family includes Qwen3-ASR-1.7B and Qwen3-ASR-0.6B, which support language identification and ASR for 52 languages and dialects. Both leverage large-scale speech training data and the strong audio understanding capability of their foundation model, Qwen3-Omni. The 1.7B version achieves state-of-the-art performance among open-source ASR models and is competitive with the strongest proprietary commercial APIs.

View model →
The platform

One platform, four layers

Start with one layer and add the others when the work asks for it. They share one key, one balance and one Activity view.

Code

Your coding agent on open models in Europe, set up with one command.

Open

Control

Keys, budgets and guardrails per team, and personal data stopped before any model sees it.

Open

Serve

Shared per token, or running for you alone, from European data centres.

Open

EU compute

Private GPUs in Europe, H100 to B300, sized for response time, generation speed and concurrent users.

Open

Try Qwen3 TTS 12Hz 0.6B CustomVoice for free

Creating an account takes a minute. Your API key works with Qwen3 TTS 12Hz 0.6B CustomVoice right away.

Get started
  • Jantine
  • Hans
  • Sander
  • Jos
  • Daan
  • Kyra
  • Margriet
  • Stan
The team behind HostYourAI