88Z AI, 17 August — Alibaba's Qwen-Audio-3.0 series voice models have launched on the Qwen AI Platform, featuring ASR, TTS, and real-time interaction models, with API support and deployment in multiple products.
At a glance
- The Qwen-Audio-3.0 series includes ASR, TTS, and real-time interaction models
- Developers can access via API or Token Plan, with deployment in Qwen App and other products
The update
Alibaba's Qwen-Audio-3.0 series voice models have officially launched on the Qwen AI Platform. The series includes three core capabilities: the Qwen-Audio-3.0-ASR large model for speech recognition, the Qwen-Audio-3.0-TTS large model for speech synthesis, and the Qwen-Audio-3.0-Realtime model for real-time voice interaction. Developers can flexibly access these model services via API interfaces or Token Plans. Currently, this latest series of voice technology has been successfully deployed and is widely used in actual products such as the Qwen App and Qwen Office, providing users with a more efficient voice interaction experience.
Sources & editorial note
This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.
- 千问AI平台Source published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.