InterconnectsArtifacts Hub
withVAILVAIL
All models

Qwen3-TTS-12Hz-1.7B-CustomVoice

byQwenQwen· 21 Jan 2026
Audio generation

A speech generation model covering 10 major languages (Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian).

Specs
Params1.7B
LicenseApache-2.0
Tags
modelsmodels/audio-generationmultilingualartifacts/18
Resources
Hugging Face — Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoicePaper / tech reportAppeared in Artifacts Log #18
Adoption · Interconnects
RAM score
—
Hugging Face Downloads
2.1M
last 30d
8.7M
all time
HF Likes
1.7K

Relative Adoption Metric contextualizes downloads against the model's size bucket.

Related Models

More from Qwen

Qwen3.6-35B-A3B
QwenQwen15 Apr 2026
Qwen3.5-397B-A17B
QwenQwen16 Feb 2026
Qwen3-Coder-Next
QwenQwen30 Jan 2026
Qwen3-ASR-1.7B
QwenQwen28 Jan 2026

Similar Models

SoulX-Podcast-1.7B
Soul-AILabSoul-AILab27 Oct 2025
Hibiki-M MLX
KyutaiKyutai04 Feb 2025
VibeVoice-1.5B
MicrosoftMicrosoft25 Aug 2025
LFM2.5-Audio-1.5B
Liquid AILiquid AI18 Dec 2025