Project AURIONAI Use-Cases Research & Innovation
Alibaba (Qwen)
speech synthesis

Qwen3-TTS 12Hz 1.7B

Open Qwen TTS model (also 0.6B size).

Alibaba (Qwen)Alibaba (Qwen)China
Qwen3-TTS architecture overview with the Qwen3 language model and multi-token prediction module.
Levelmodel
Classspeech synthesis
Parameters1.7B
Contextnot in the notes
Released22 Jan 2026
Opennessopen weights permissive
Runs onconsumer GPU
Statusactive

Lineage

successor
Qwen3-TTS 12Hz 1.7B to Qwen-Audio-3.1-TTS-Plus: successor, low confidenceQwen3-TTS 12Hz 1.7BQwen3-TTS 12Hz 1.7BAlibaba (Qwen), Jan 2026Qwen-Audio-3.1-TTS-PlusQwen-Audio-3.1-TTS-PlusAlibaba (Qwen), Sep 2026
Alibaba (Qwen)Qwen-Audio-3.1-TTS-Plus is a child (successor)low confidencenotes
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 2 models. Confidence and evidence are the notes' own.

R&D Topics

Large-scale zero-shot text-to-speechproduced by

Identity

Developer
Alibaba (Qwen)
Family
not in the notes
Released
22 Jan 2026 sourcesregistry date
Weights published
–
Record checked
10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
autoregressive Discrete multi-codebook LM
Total parameters
1.7B sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
text
Output
audio
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
open weights permissive
Licence
Apache License 2.0 sources
Access routes
open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
consumer GPU
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
10 languages; Indonesian not listed
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice , Hugging Face huggingface.co https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Qwen3-TTS 12Hz 1.7B", https://aurion.semai.id/models/alibaba-qwen3-tts-12hz-1-7b/, records of October 2026.