Speech and audio·EASYHUB JOURNAL
Qwen3-TTS opens compact multilingual speech models
What changed
Qwen’s speech family offers different sizes and controls for multilingual generation. Reference voices and cloning functions require authorized material; access to a model does not grant rights to another person’s voice.
- Original title
- 阿里千问：Qwen3-TTS 语音生成模型全家桶开源上线
- Source
- IT之家 · www.ithome.com
- Author or account
- 千问 Qwen 微信公众号（报道援引）
- Topic
- Speech and audio
- Source month
- 2026-01
This is a concise EasyHub summary of the linked source, not the full report or original reporting. Availability and preview conditions are described in the summary and original.
Summary page published · Editorial information