Qwen3 TTS
Fewer than 5 people recommend it so far, so there's no written verdict. Here is what commenters said.
3recommend
0warn against
Jan 23, 2026first mention
Oct 7, 2026latest mention
Why people recommend it
“QWEN3 TTS has a “clone” feature. You can use the local version, give it a voice reference and text”
“I use mlx-audio almost daily with mlx-community/Qwen3-TTS-12Hz-1.7B-Base-bf16 (for voice cloning)”
Show 1 more
“I just tried qwen 3 tts and it was mind blowingly good”
Caveats and dissent
No one in these comments warned against it.
Threads where it came up
- Ask HN: Are there AI models for generating sounds based on a text and reference? 1 mention
- Nativ: Run frontier open models locally on your Mac 1 mention
- Show HN: One UI to voice-control local and remote AI coding agents via tmux 1 mention
- Qwen3-Coder-Next 1 mention
- Ask HN: What's the current best local/open speech-to-speech setup? 1 mention
- Qwen3-TTS Family Is Now Open Sourced: Voice Design, Clone, and Generation 1 mention
Also written as Qwen3-TTS. Data: qwen3-tts.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 6
“QWEN3 TTS has a “clone” feature. You can use the local version, give it a voice reference and text”
“I use mlx-audio almost daily with mlx-community/Qwen3-TTS-12Hz-1.7B-Base-bf16 (for voice cloning)”
“Chatterbox or Qwen3-TTS for voices”
“I just tried qwen 3 tts and it was mind blowingly good”
“Qwen3 TTS (with voice cloning support!)”
“Curious how it compares to last week’s release of Kyutai’s Pocket-TTS”