88Z AI, 29 June — Alibaba's Tongyi Qianwen team has launched a standalone AI voice input method called 'Qianwen Input', emphasizing casual speech and polished writing. Built on the Qianwen large model's CosyVoice capabilities, it converts speech to text while understanding semantics, removing filler words, and correcting slips to structure spoken language into written text. It supports speeds up to 300 characters per minute, recognition of nine dialects, and mixed Chinese-English speech.
At a glance
- Integrates CosyVoice to remove fillers and correct errors, converting speech into structured text
- Supports input speeds up to 300 chars/min, with recognition for 9 dialects and mixed Chinese-English
The update
Alibaba's Tongyi Qianwen team has officially launched 'Qianwen Input', a standalone AI voice input method. Centered on the concept of 'casual speech, polished writing', the app aims to enhance the user's voice input experience. Technically, it deeply integrates the CosyVoice capabilities of the Tongyi Qianwen large model. Beyond basic speech-to-text conversion, it features strong semantic understanding. The system automatically identifies and removes filler words from spoken language, intelligently corrects slips, and efficiently organizes fragmented, unstructured daily speech into standardized, clear written text. Furthermore, Qianwen Input delivers impressive performance, supporting rapid input speeds of up to 300 characters per minute. In terms of language compatibility, it offers accurate recognition for nine dialects and allows users to speak in a mix of Chinese and English, catering to diverse input needs.
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.
- 千问输入法Source published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.