The open-source voice synthesis studio powered by Qwen3-TTS.

A ComfyUI custom node integration for multi-engine multi-language Text-to-Speech and Voice Conversion. Supports: RVC, Echo-TTS, Qwen3-TTS, Cozy Voice 3, Step Audio EditX, IndexTTS-2, Chatterbox (classic and multilingual 23-lang), F5-TTS, Higgs Audio 2 and VibeVoice with unlimited text length, SRT timing, Character support, and many audio tools

Run Qwen3-TTS text-to-speech locally on Mac (M1/M2/M3/M4). Voice cloning, voice design, custom voices. 100% offline using MLX.

AI-powered multi-voice audiobook generator — LLM script annotation, voice cloning, voice design, LoRA training, per-line style control, and export to MP3, chaptered M4B, or Audacity multi-track. Built on Qwen3-TTS.

MimikaStudio - A local-first application for macOS (Apple Silicon) + Agentic MCP Support

Japanese GUI + Whisper auto-transcription for Qwen3-TTS. RTX 5090 tested.

Easy fine-tuning for Qwen3-TTS: Fast voice cloning and high-quality multilingual speech synthesis.

Qwen3-TTS is an open-source series of TTS models developed by the Qwen team

Home Assistant integrates Alibaba Cloud's BaiLian Platform TTS

A Simple webui and api for cloning voices with Qwen3-TTS

Enhanced Qwen3-TTS voice cloning GUI with multi-reference samples, variation generation, and audio preprocessing.

基于阿里巴巴 Qwen3-TTS 模型（17 亿参数）的全栈文本转语音 Web 应用，支持语音定制、语音设计和语音克隆，有声书生成功能。A text-to-speech web application based on Qwen3-TTS, supporting custom voice, voice design, voice cloning, and audiobook generation..

Free voice cloning and TTS for creators using Qwen3-TTS on Google Colab. Clone your voice with just a few seconds of audio. Complete guide to build your own notebook.

Qwen3-TTS Audiobook Studio: Ultimate local multi-role AI audiobook generator. Built-in 3s Voice Clone & Design. Portable one-click launch for Mac/Win. 极致本地 AI 有声书制作工坊。

C++ implementation of Qwen3-TTS running on top of ONNX Runtime.

A desktop interface for the powerful Qwen3-TTS model (1.7B CustomVoice). Run offline, ultra-low latency text-to-speech with emotive control directly on your GPU.

Pure C inference engine for Qwen3-TTS text-to-speech. No Python, no PyTorch — just C and BLAS. Supports 0.6B and 1.7B models, 9 voices, 10 languages.

🗣 Java Text to Speech (JSAPI2) engines (google cloud, cocoa, open jtalk, aquestalk(ゆっくり), voicevox(ずんだもん), coeiroink, aivisspeech, google genai, qwen3-tts)

🎙️ Qwen3-TTS-DubFlow: An open-source, human-in-the-loop AI dubbing workbench for novels, games, podcasts, and more. Features a "Design-then-Clone" workflow powered by Qwen3-TTS to achieve consistent identity and context-aware emotional performance.