iFlytek Speech RecorderLatest version

Introduction to the iFlytek Yujì APP

iFlyText is an intelligent voice-based cloud note-taking application developed by iFlytek, designed for professionals in offices, journalists, creators, and learners who need to record and organize information efficiently. Based on iFlytek’s speech recognition technology, it converts real-time speech, meeting recordings, and external audio into editable text; moreover, by integrating OCR, rich-text editing, text reading aloud, reminder functions, and multi-device synchronization, it enables the entire process of recording and organizing information.

Main functions of the iFlytek Yujì app

• Real-time voice transcription:Speaking into a smartphone can be directly converted into text, making it ideal for capturing ideas, dictating articles, and taking quick notes, thus reducing the time required to type out long texts manually.
• Continuous input for a long time:The official voice input feature allows for continuous recording for up to 120 minutes, so users do not need to interrupt the process frequently during long interviews, discussions, or creative tasks.
• Multilingual and dialect recognition:It supports voice transcription in both Chinese and English, as well as various dialects, enabling speech from different linguistic backgrounds and accents to be converted into unified written text.
• Meeting transcript:During a meeting, it is possible to record audio simultaneously and convert it into text, which is useful for compiling key points from meetings, taking class notes, and preparing interview materials, thus reducing the risk of missing important information.
• Edit while listening:The recorded audio corresponds to the transcribed text, allowing users to listen to specific segments again and make immediate adjustments to the recognition results, thus making the proofreading process more intuitive and efficient.
• Import external audio:Existing recordings of interviews, training sessions, or meetings can be imported for transcription; according to the official information, an hour’s worth of audio can be transcribed in about five minutes, which makes it suitable for processing large amounts of existing material at once.
• OCR image recognition:It supports batch processing of images to extract Chinese and English text from them, as well as recognizing handwritten text; it can be used to create reading notes, enter paper-based documents, and organize photo content.
• Graphic note editor:Notes support a mixed layout of text and images, and offer rich text features such as titles, bolding, and citations, which make it easy to further process the transcribed content into well-structured documents.
• Voice reading of notes:Text notes can be converted into audio playback, with multiple speakers and different voices available; this is ideal for listening to content while commuting, driving, or when it’s not possible to keep looking at the screen.
• Identification of professional fields:Industry-specific voice engines are provided for professional contexts such as healthcare and law, enhancing the recognition of specialized terminology to meet the needs of professional interviews, recording, and content creation.
• Tasks and Reminders:Users can manage to-do items and reminders while recording content, linking meeting outcomes, personal notes, and action plans together.
• Multi-device cloud synchronization:Login is supported on devices such as iOS, Android, and web browsers; notes and related materials can be saved synchronously, making it easy to view and edit them on both smartphones and computers.
• Categorized management and sharing:Notes can be organized by category and shared in various ways, which makes it easier to search through large amounts of records. It also facilitates the sharing of interview transcripts, meeting notes, and learning materials with others.