freym
freym / models prices / Qwen-Audio-3.0-TTS

Qwen-Audio-3.0-TTS

Qwen-Audio-3.0-TTS is Alibaba's text-to-speech model, introduced July 23, 2026 with both real-time and high-quality synthesis options.

By Alibaba · text-to-speech · Last update tracked July 23, 2026 · Page updated 2026-08-08

Key facts

DeveloperAlibaba
Categorytext-to-speech
Notable forReal-time and high-quality synthesis modes.
Tracked announcements1

Announcement timeline

model-release

Alibaba Introduces Qwen-Audio-3.0-TTS with Real-Time and High-Quality Options

Alibaba Introduces Qwen-Audio-3.0-TTS with Real-Time and High-Quality Options

Alibaba released Qwen-Audio-3.0-TTS, a new text-to-speech model available in Flash (real-time) and Plus (high-quality) variants. The model features fine-grained control through inline tags for emotion and vocal effects, plus free-style natural language steering.

FAQ

What is Qwen-Audio-3.0-TTS?

Qwen-Audio-3.0-TTS is Alibaba's text-to-speech model, introduced July 23, 2026 with both real-time and high-quality synthesis options.

Who makes Qwen-Audio-3.0-TTS?

Qwen-Audio-3.0-TTS is developed by Alibaba. This page tracks its official announcements as they happen.

What is the latest Qwen-Audio-3.0-TTS news?

Alibaba Introduces Qwen-Audio-3.0-TTS with Real-Time and High-Quality Options (July 23, 2026). Alibaba released Qwen-Audio-3.0-TTS, a new text-to-speech model available in Flash (real-time) and Plus (high-quality) variants. The model features fine-grained control through inline tags for emotion and vocal effects, plus free-style natural language steering.