# QwenLM/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.

Repository: https://github.com/QwenLM/Qwen3-TTS
Canonical: https://ross.abutalabs.com/products/qwen3-tts
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-03-17T06:38:41+00:00

## Health v2 (maintenance only)
Score: 48/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 72, release rhythm 35, longevity 16
- inputs: {"age_days": 224, "days_push": 169, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 13113, forks 1698 (observed 2026-08-28T04:11:02.182739+00:00)

## What it is
Qwen3-TTS is a series of open-source text-to-speech models from Alibaba's Qwen team, supporting expressive and streaming speech generation, free-form voice design, and voice cloning across 10 languages. It ships as a Python package with a tokenizer, local web UI demo, vLLM support, and fine-tuning tooling.

## Use cases
- generate human-like speech from text
- clone a voice from a short audio sample
- design a custom voice from a natural language description
- stream text-to-speech audio in real time
- build a multilingual voice assistant with expressive speech
- fine-tune a TTS model on my own voice data
- serve TTS models with vLLM for production inference

## When to choose
- you need high-quality, expressive multilingual TTS with voice cloning or voice design
- you want an open-weights Apache-2.0 TTS model you can self-host or fine-tune
- you need streaming speech generation integrated with the Qwen/LLM ecosystem

## When to avoid
- you need a lightweight TTS that runs on CPU-only or edge devices
- you only need a hosted API without managing GPU infrastructure
- you need languages outside the 10 supported ones

## Facets
- artifact type: library
- maturity: active
- function: tts, speech-recognition, machine-learning, llm-inference
- domain: speech-processing, artificial-intelligence
- platform: python, cross-platform
- tags: text-to-speech, voice-cloning, voice-design, streaming-speech, qwen, multilingual, vllm, audio-generation, natural-language-processing, gpu

## Member repositories
- QwenLM/Qwen3-TTS (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:02.182739+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:13:31.256063+00:00, confidence not recorded.
  - readme: https://github.com/QwenLM/Qwen3-TTS (fetched 2026-08-28T04:11:02.182739+00:00, sha cb0918d23805)
- Data as of 2026-08-30T08:39:29.467469+00:00.