Design Arena Elo (models/audiorealism)Source: Design Arena Leaderboards data · Nov 2026
Alibaba · Speech
Qwen-Audio-3.0-TTS Flash
Newer version: Qwen Audio 3.1 TTS Flash. Our catalogue has no release date for Qwen-Audio-3.0-TTS Flash. We compared the version names in our catalogue.
Alibaba's low-latency Qwen-Audio-3.0 text-to-speech model optimized for real-time interaction across 16 languages. Generates speech via the /v1/audio/speech endpoint.
- Maker's price
- $15.00 /1M chars
- Max context
- 20K
- Listings
- 3
- Providers
- 2
Evidence and sources
International storefront (alibabacloud.com) is Singapore-incorporated; mainland operating entity 杭州阿里云智能科技有限公司 (Hangzhou).
Maker HQ: CN (source)
All rankings:
#602 on OpenRouter today
#621 on OpenRouter this week
#658 on OpenRouter this monthSources: LiteLLM data, LLMGateway dataPrimary data from LiteLLM
from LLMGateway: name, description
Input & output
as stated by the model's providersText
Audio
Also known as: dashscope/qwen-audio-3.0-tts-flash
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works