Qwen Releases Open-Source Voice Cloning Model
The new 600-million-parameter Qwen3-TTS model can generate speech in multiple languages and clone voices from short audio clips.
The Qwen team, part of Alibaba, has released a new open-source model for generating human-like speech. Named Qwen3-TTS, this initial release is a 600-million-parameter base model designed for text-to-speech (TTS) applications, making another powerful generative audio tool available to developers.
The model's key capabilities are its multilingual support and its capacity for voice cloning. This allows it to not only generate speech in various languages but also to mimic a specific person's voice using only a short audio sample as a reference. This feature, often called zero-shot voice cloning, is a significant capability for creating custom voice assistants, dynamic audio content, and accessibility tools.
A Permissive Foundation
Released under the permissive Apache 2.0 license, Qwen3-TTS provides a strong alternative to proprietary text-to-speech APIs. Its open nature encourages experimentation and allows developers to build upon it without restrictive licensing, fostering innovation in the open-source AI audio space.
The model, officially designated Qwen3-TTS-12Hz-0.6B-Base, is available now for download and use. As a "base" model, it serves as a solid foundation intended for further fine-tuning on specific tasks or voices to achieve higher quality and more specialized outputs.
Sources
- Visit
Qwen/Qwen3-TTS-12Hz-0.6B-Base
Hugging Face
More from Qwen · Alibaba
All Qwen · Alibaba releases →Qwen-Audio-3.1-ASR Adds Speaker-Aware Transcription
Alibaba's new open audio-language model transcribes and diarizes speech across 30 languages under an Apache 2.0 license.
Qwen-Image-2.1-Turbo targets faster generation
Alibaba's Qwen team ships a distilled, few-step variant of its image model built for speed.
Qwen-Image-2.1 Adds RGBA to Image Generation
Alibaba's Qwen team updates its open image model with transparency support and joint text-to-image and editing capabilities.
More in Text → Speech
All Text → Speech →
Liquid AI's LFM3-Omni-2B brings any-to-any AI to the edge
The 2-billion-parameter model combines vision, audio and speech-to-speech in a package small enough to run on device.
IBM's Granite Switch 4.1 Unifies Chat, Logic, Speech
A single endpoint now routes text conversation, decision-making, and speech synthesis across IBM's Apache-licensed Granite line.
Fish Audio's Drama 3 brings MoE to open TTS
The open-source speech model pairs a 35B mixture-of-experts backbone with voice cloning and directed performance control.
0 comments
No comments yet. Be the first to weigh in.