88Z AI, 10 August — Alibaba has released CosyVoice Studio, the first one-stop AI voice platform in China. Built on the self-developed Qwen-Audio model, it integrates three core modules for voice recording, agents, and audio creation.
At a glance
- The platform is built on the Qwen-Audio model and integrates modules for voice recording, agents, and audio creation
- It supports structured text generation, real-time voice agent creation, and document-to-audio conversion
The update
Alibaba has officially launched CosyVoice Studio, the first one-stop artificial intelligence voice platform in China. Built on the self-developed Qwen-Audio model, the platform deeply integrates three functional modules: CosyFlow for voice recording, CosyAgent for voice agents, and CosyCreative for audio creation. CosyFlow supports speech transcription enhanced with semantic understanding to generate structured text. CosyAgent enables users to quickly create voice agents with real-time interaction capabilities using natural language commands. Furthermore, the CosyCreative module allows document uploads to automatically generate podcasts and multi-character audiobooks, providing end-to-end support for audio content production.
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.
- 阿里云Source published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.