Skip to content
Agents tracked: 492 Releases (7d): 545 Agent status: 1 with issuesSince last limit reset: Claude 9d · Codex 7d For AI agents: Markdown Updated Nov 20, 2026

Qwen3-TTS

by Qwen team (Alibaba)

Multilingual TTS family (10 languages) with preset voices, voice design from text prompts and 3-second voice cloning.

Voiceover (text-to-speech) Code libraryOpen source

GitHub repoWebsite

2. Commercial use: LICENSE on GitHub

“each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare Derivative Works of, publicly display, publicly perform, sublicense, and distribute”

Apache 2.0 allows commercial use of the models and code.

LICENSE on GitHub

License checked Oct 25, 2026 against 1 official page. Tap a verdict to see its source. How we checked Report an error

Qwen3-TTS: open voices that read your text aloud

Qwen3-TTS is a free, open family of AI voice models from the Qwen team at Alibaba that turns written text into natural speech. It speaks 10 languages, including English, Russian and Chinese. You can pick a ready voice, describe a new voice in words, or copy a voice from a 3-second recording, and run it all on your own computer.

Where you can use it

Voiceover with a ready voice

Pick one of nine ready voices and get a sound file for a video, a lesson or an app screen. You can add a short note such as "Very happy." to set the mood.

Describe a new voice in words

Write how the voice should sound, such as age, tone and emotion, and the model makes a matching voice. Handy for game characters or story narrators.

Speak in a voice from a short clip

Give a few seconds of recorded speech and its words, and new text is read in that voice. Use your own voice or one you have permission to use.

One character voice for many lines

Design a voice once, save it as a reusable sample, and use it for every line of a game, comic dub or course, so the character always sounds the same.

Try voices in a local web page

Start a small web page on your computer to type text, pick a voice and listen, before writing any code.

Read articles aloud in several languages Idea

Add a Listen button to blog posts or help pages and make the audio in the reader's language with the same voice.

As reported by Qwen team (Alibaba): End-to-end synthesis latency as low as 97ms..

Qwen3-TTS popularity

40 / 100
Gid Score, same scale as developer tools
14,511
GitHub stars
90.9K
PyPI downloads, last 7 days
+45.7% in 4 weeks
1
AI-agent projects using it, from our repo scan of 1,606
Qwen3-TTS: downloads per weekPyPI, qwen-tts 89,999
Qwen3-TTS: GitHub starsQwenLM/Qwen3-TTS 14,511

Downloads from pypistats.org, stars from GitHub, checked Nov 19, 2026. How the Gid Score is calculated

How to start

Tell your AI assistant

“In a fresh Python 3.12 env, install qwen-tts==0.1.1, load Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice and write my script to a wav file with speaker "Ryan" in English; keep the license notice if we ship the model files.”

Show codeStep 1 or Step 2 or Step 3

Make a fresh Python 3.12 environment so its pinned packages do not clash with others.

conda create -n qwen3-tts python=3.12 -y
conda activate qwen3-tts

Mistakes to avoid

pip install qwen-tts into an existing project environment
create a fresh env first (conda create -n qwen3-tts python=3.12)

The package pins exact versions of transformers and accelerate that can clash with other packages.

attn_implementation="flash_attention_2" with float32 or on unsupported hardware
load with dtype=torch.bfloat16 (or float16) on a supported GPU, or leave out attn_implementation

FlashAttention 2 only works in half precision on compatible hardware.

generate_voice_clone(text=..., ref_audio=clip) without ref_text
pass ref_text with the exact words of the clip, or set x_vector_only_mode=True and accept lower similarity

The clone model expects the transcript of the reference clip.

calling generate_voice_clone many times with the same ref_audio
build the prompt once with create_voice_clone_prompt and pass voice_clone_prompt

Reusing the prompt avoids recomputing the reference features every time.

License

Apache-2.0 license. Apache 2.0 license: free to use in personal and paid products, and you may change and share the models and code. When you pass the files on, include the license and keep the notices.

Commercial use
Yes

“each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare Derivative Works of, publicly display, publicly perform, sublicense, and distribute” LICENSE on GitHub

Credit
Required

“You must give any other recipients of the Work or Derivative Works a copy of this License” LICENSE on GitHub

Inside your app or game
Can ship inside your app

“each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare Derivative Works of, publicly display, publicly perform, sublicense, and distribute” LICENSE on GitHub

Pass the files on to your users
With conditions

Passing on the weights or code is allowed with the license copy and notices kept.

“You must give any other recipients of the Work or Derivative Works a copy of this License” LICENSE on GitHub

AI training
Not stated
Bots and bulk downloads
Not stated

AllowedWith conditionsNot allowedNot stated or not checked yet

Is Qwen3-TTS free for commercial use? The full answer Not legal advice. Check the license page before you ship.

For your agent

License rules tell your agent what it may do with Qwen3-TTS. Paste them into your prompt or AGENTS.md.

License rules
- Qwen3-TTS (Voiceover (text-to-speech)). Multilingual TTS family (10 languages) with preset voices, voice design from text prompts and 3-second voice cloning. Price: free; commercial use OK; credit required.
  Connect: PyPI qwen-tts.
  Rule: Apache-2.0 weights and code; commercial use and products allowed.
  Rule: When redistributing the weights or code, include the license and keep notices.
  Rule: No credit is required inside the generated audio.
  License: https://github.com/QwenLM/Qwen3-TTS/blob/main/LICENSE (checked 2026-10-25; details: https://agentgid.com/assets/qwen3-tts/)
Can an agent use it by itself?
Yes.

Agent installs a package or loads it from a CDN.

Install
pip install qwen-tts
API, key or account
Not needed. Everything runs on your side.
MCP server
None found
Credit line, if you want one
Voice: Qwen3-TTS (Qwen team, Alibaba), Apache License 2.0
This card for machines

Alternatives

Qwen3-TTS This page

Free Commercial OK PyPI

Chatterbox

Pick Chatterbox when you want an MIT-licensed voice model with cloning in 23 languages and a built-in audio watermark.

Free Commercial OK PyPI

CosyVoice 3

Pick CosyVoice 3 when you need many Chinese dialects as well as voice cloning and streaming.

Free Commercial OK Download

Piper

Pick Piper for a small, fast voice engine that runs on modest computers, with voices under their own licenses.

Free With conditions PyPI

VoiceStudio

Local desktop app for voice cloning, voice design, video dubbing, dictation and transcription in 646 languages, with a local API and an MCP server for agents.

Free With conditions MCP, API

VibeVoice

Long-form multi-speaker TTS for podcast-style dialogue, up to 90 minutes and 4 speakers, in English and Chinese.

Free With conditions Download

All voiceover (text-to-speech)

Questions

Does it speak Russian?

Yes. Russian is one of the ten languages, together with English, Chinese, Japanese, Korean, German, French, Portuguese, Spanish and Italian.

Can I use the voices in a paid app or video?

Yes. The models and code are under Apache 2.0, which allows commercial use; keep the license when you pass files on.

How long a recording do I need to copy a voice?

About 3 seconds of speech, together with the words spoken in it.

Can I copy a voice without typing out the words of the sample?

Yes, with x_vector_only_mode=True, but the copy may sound less like the original.