Model reference · open weights

Qwen3-TTS-12Hz

Available as managed deployment Audio theoracleguy · community Text→speech 2 variants 780 dl/mo

Qwen3-TTS-12Hz is an open-weight audio or speech model from theoracleguy. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released bytheoracleguy
TypeAudio & music
TaskText→speech
Parameters (lead)915M
Runs withmlx-audio
Released2026-03-14
Popularity780 downloads / month
LicenceOpen weights

About

What Qwen3-TTS-12Hz is

This model was converted to MLX format from Qwen/Qwen3-TTS-12Hz-0.6B-Base using mlx-audio version 0.3.0.

Refer to the original model card for more details on the model.

Read the full model card

Use with OpenVox

This model can also be used with OpenVox, a desktop application for running compatible AI voice and text-to-speech models locally through a graphical interface.

After the required model files are downloaded, compatible workflows can run locally and can also be accessed through OpenVox API and MCP integrations.

Available features depend on the capabilities of the selected model. OpenVox is a third-party application and is not affiliated with or endorsed by the original model authors or maintainers.

Use with mlx-audio

pip install -U mlx-audio

CLI Example:

python -m mlx_audio.tts.generate --model mlx-community/Qwen3-TTS-12Hz-0.6B-Base-bf16 --text "Hello, this is a test."

Python Example:

from mlx_audio.tts.utils import load_model
from mlx_audio.tts.generate import generate_audio

model = load_model("mlx-community/Qwen3-TTS-12Hz-0.6B-Base-bf16")
generate_audio(
    model=model,
    text="Hello, this is a test.",
    ref_audio="path_to_audio.wav",
    file_prefix="test_audio",
)

From the published model card. Full card on the HuggingFace links in the sidebar.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys theoracleguy-qwen3-tts-12hz for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (theoracleguy-qwen3-tts-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="theoracleguy-qwen3-tts-12hz" -F file=@audio.mp3

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

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