QwenLM/Qwen3-TTS

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

13113 stars · 1698 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

library · maturity active

tts speech-recognition machine-learning llm-inference speech-processing artificial-intelligence python cross-platform text-to-speech voice-cloning voice-design streaming-speech qwen multilingual vllm audio-generation natural-language-processing gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="QwenLM/Qwen3-TTS")