CPcpburns2009·Feb 17, 2026
You're looking for text-to-speech. Qwen actually has a model and library for this: Qwen3-TTS [1].
[1]: https://github.com/QwenLM/Qwen3-TTS
In Qwen3.5: Towards Native Multimodal AgentsQwenLM
Qwen3-TTS
Python2026–2026
QwenLM / Qwen3-TTS
Qwen3-TTS
Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice cloning.
3Distinct people
3Mentions
0Explicit recommenders
14.4KGitHub stars
What to know before exploring
What it is
Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice cloning.
GitHub
Where it is used
No documented product use has been verified yet.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 5:04:57 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by day3 dated mentions
Observed mentions: 2026-01-23 00:01:16 UTC to 2026-02-17 14:37:49 UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| Jan 23 | 2026-01-23 00:00:00 UTC | 2026-01-24 00:00:00 UTC | 1 | 0 | 1 |
| Jan 24 | 2026-01-24 00:00:00 UTC | 2026-01-25 00:00:00 UTC | 0 | 0 | 0 |
| Jan 25 | 2026-01-25 00:00:00 UTC | 2026-01-26 00:00:00 UTC | 1 | 1 | 0 |
| Jan 26 | 2026-01-26 00:00:00 UTC | 2026-01-27 00:00:00 UTC | 0 | 0 | 0 |
| Jan 27 | 2026-01-27 00:00:00 UTC | 2026-01-28 00:00:00 UTC | 0 | 0 | 0 |
| Jan 28 | 2026-01-28 00:00:00 UTC | 2026-01-29 00:00:00 UTC | 0 | 0 | 0 |
| Jan 29 | 2026-01-29 00:00:00 UTC | 2026-01-30 00:00:00 UTC | 0 | 0 | 0 |
| Jan 30 | 2026-01-30 00:00:00 UTC | 2026-01-31 00:00:00 UTC | 0 | 0 | 0 |
| Jan 31 | 2026-01-31 00:00:00 UTC | 2026-02-01 00:00:00 UTC | 0 | 0 | 0 |
| Feb 1 | 2026-02-01 00:00:00 UTC | 2026-02-02 00:00:00 UTC | 0 | 0 | 0 |
| Feb 2 | 2026-02-02 00:00:00 UTC | 2026-02-03 00:00:00 UTC | 0 | 0 | 0 |
| Feb 3 | 2026-02-03 00:00:00 UTC | 2026-02-04 00:00:00 UTC | 0 | 0 | 0 |
| Feb 4 | 2026-02-04 00:00:00 UTC | 2026-02-05 00:00:00 UTC | 0 | 0 | 0 |
| Feb 5 | 2026-02-05 00:00:00 UTC | 2026-02-06 00:00:00 UTC | 0 | 0 | 0 |
| Feb 6 | 2026-02-06 00:00:00 UTC | 2026-02-07 00:00:00 UTC | 0 | 0 | 0 |
| Feb 7 | 2026-02-07 00:00:00 UTC | 2026-02-08 00:00:00 UTC | 0 | 0 | 0 |
| Feb 8 | 2026-02-08 00:00:00 UTC | 2026-02-09 00:00:00 UTC | 0 | 0 | 0 |
| Feb 9 | 2026-02-09 00:00:00 UTC | 2026-02-10 00:00:00 UTC | 0 | 0 | 0 |
| Feb 10 | 2026-02-10 00:00:00 UTC | 2026-02-11 00:00:00 UTC | 0 | 0 | 0 |
| Feb 11 | 2026-02-11 00:00:00 UTC | 2026-02-12 00:00:00 UTC | 0 | 0 | 0 |
| Feb 12 | 2026-02-12 00:00:00 UTC | 2026-02-13 00:00:00 UTC | 0 | 0 | 0 |
| Feb 13 | 2026-02-13 00:00:00 UTC | 2026-02-14 00:00:00 UTC | 0 | 0 | 0 |
| Feb 14 | 2026-02-14 00:00:00 UTC | 2026-02-15 00:00:00 UTC | 0 | 0 | 0 |
| Feb 15 | 2026-02-15 00:00:00 UTC | 2026-02-16 00:00:00 UTC | 0 | 0 | 0 |
| Feb 16 | 2026-02-16 00:00:00 UTC | 2026-02-17 00:00:00 UTC | 0 | 0 | 0 |
| Feb 17 | 2026-02-17 00:00:00 UTC | 2026-02-18 00:00:00 UTC | 1 | 0 | 1 |
What Hacker News says
3 sourcesQwen3-TTS: Ultra-Low Latency (97ms), Voice Cloning and OpenAI-Compatible API
1 points · Open discussionI just followed the Quickstart[1] in the GitHub repo, refreshingly straight forward. Using the pip package worked fine, as did installing the editable version using the git repository. Just install the CUDA version of PyTorch[2] first.
The HF demo is very similar to the GitHub demo, so easy to try out.
pip install torch torchvision --index-url https://download.pytorch.org/whl/cu128
pip install qwen3-tts
qwen-tts-demo Qwen/Qwen3-TTS-12Hz-1.7B-Base --no-flash-attn --ip 127.0.0.1 --port 8000
That's for CUDA 12.8, change PyTorch install accordingly.
Skipped FlashAttention since I'm on Windows and I haven't gotten FlashAttention 2 to work there yet (I found some precompiled FA3 files[3] but Qwen3-TTS isn't FA3 compatible yet).
[1]: https://github.com/QwenLM/Qwen3-TTS?tab=readme-ov-file#quick...
[2]: https://pytorch.org/get-started/local