Qwen / text-to-speech updated 6 months ago

Qwen3-TTS-12Hz-0.6B-Base

Name: Qwen3-TTS-12Hz-0.6B-Base
Author: Qwen

Qwen3-TTS is a family of advanced multilingual, controllable, robust, and streaming text-to-speech models. Trained on over 5 million hours of speech data spanning 10 languages, Qwen3-TTS supports state-of-the-art 3-second voice cloning and description-based control.

Params

910 M

Context

—

Downloads 30d

445 K

Likes

273

Commercial use: allowed apache-2.0 Not gated SAFETENSORS 10 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

445 K410 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	2.5 GB	3.4 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: Qwen3TTSForConditionalGeneration
Parameters: 910 M
Tensor type: BF16
Licence: apache-2.0
First seen on the Hub: 2026-01-21
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

Kokoro-82M 12.0 M XTTS-v2 9.2 M chatterbox 2.5 M Qwen3-TTS-12Hz-1.7B-CustomVoice 2.3 M Qwen3-TTS-12Hz-0.6B-CustomVoice 1.6 M Kokoro-82M-v1.0-ONNX 1.4 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB