YOU ARE VIEWING ONE ITEM FROM THE AICRIER FEED

OpenRouter launches Qwen-Audio-3.0-TTS Flash and Plus

AICrier tracks AI developer news across Product Hunt, GitHub, Hacker News, YouTube, X, arXiv, and more. This page keeps the article you opened front and center while giving you a path into the live feed.

// WHAT AICRIER DOES

7+

TRACKED FEEDS

24/7

SCRAPED FEED

Short summaries, external links, screenshots, relevance scoring, tags, and featured picks for AI builders.

OpenRouter launches Qwen-Audio-3.0-TTS Flash and Plus
OPEN LINK ↗
// 6h agoMODEL RELEASE

OpenRouter launches Qwen-Audio-3.0-TTS Flash and Plus

OpenRouter has made Alibaba's Qwen-Audio-3.0-TTS Flash and Plus text-to-speech models available, supporting 16 languages and inline emotional cues like [gasp] and [giggles]. Qwen-Audio-3.0-TTS Plus emphasizes speech naturalness and audio fidelity, while Flash targets low-latency real-time interactions and voice cloning.

// ANALYSIS

Bringing expressiveness control and low-latency TTS options to OpenRouter lowers the barrier for developers building interactive, voice-driven AI applications.

  • Qwen-Audio-3.0-TTS Plus focuses on audio quality and voice fidelity across 16 languages.
  • Qwen-Audio-3.0-TTS Flash prioritizes speed and low-latency interaction with flexible voice cloning.
  • Support for inline cues like [gasp] and [giggles] enables fine-grained emotional nuance in speech generation.
// TAGS
ttsqwenalibabaopenrouteraudiovoice-cloningai-voicespeech

DISCOVERED

6h ago

2026-07-23

PUBLISHED

7h ago

2026-07-23

RELEVANCE

8/ 10

AUTHOR

OpenRouter