Speech-to-text assistantLatest version

Introduction to the audio-to-text assistant app

The transcription assistant is an Android AI voice processing application developed by Shanghai Dongqi Information Technology Co., Ltd. It is suitable for office workers, students, and content creators who need to organize meeting recordings, interviews, course materials, video content, and voice memos. Based on audio and video recognition, it incorporates functions such as separating multiple speakers’ voices, providing multilingual translation, audio editing, text-to-speech synthesis, image text recognition, and automatic subtitles, thereby enabling users to carry out the process of capturing sound, organizing it, editing it, and exporting it all from their smartphones.

Main functions of the audio-to-text assistant app

• Real-time audio to text conversion:Once recording begins, you can speak while the text is generated, which is suitable for recording meetings, interviews, and classroom sessions, thereby reducing the time needed to transcribe what was said after the event.
• System sound recording:It enables the recording of system audio with clear sound quality, making it convenient to save courses, meetings, or other audio content played on the phone that needs to be organized later.
• External audio recognition:Existing audio files can be imported from mobile phones, file repositories, or common communication channels; the recognition system converts them into editable text, making it suitable for working with historical recordings and voice files sent by others.
• Batch file transcription:It allows for the import of multiple audio files at once for processing, thereby eliminating the need to carry out individual operations repeatedly; it is suitable for organizing recordings from multiple meetings, interviews, or courses in a centralized manner.
• Compatibility with multiple audio formats:It can recognize common audio formats such as MP3, M4A, and FLAC, and export the results as text documents or subtitle files for further editing and archiving.
• Separation of multiple speakers’ voices:AI is able to distinguish between different statements in multi-person conversations and separate them into individual sentences, enabling users to more quickly identify what was said during meetings and interviews.
• Multilingual and dialect translation:It offers online translation, audio translation, file translation, voice translation, and real-time translation in various dialects and languages, for use in cross-lingual communication and document organization.
• Video to text and subtitles:It can identify the sounds in a video and extract the spoken words, turning them into text or subtitles; it is suitable for creating scripts and subtitles for courses, interviews, and short videos.
• Video and audio extraction:It is possible to extract the sound from video files and save it as audio material, allowing users to proceed with further processing such as transcription, editing, or adding voiceovers.
• Text-to-speech narration:AI is used to convert inputted text into natural-sounding speech, allowing for adjustments to the speaking speed, tone, and pauses; it is suitable for use in advertising copy, book narration, in-store announcements, and video voiceovers.
• Audio editing:It supports audio merging, cropping, splitting, reverse playback, fade in/fade out, volume adjustment, as well as speed and pitch changes, making it easy to edit audio recordings directly on a smartphone.
• Stereo processing:It offers functions such as stereo surround enhancement, channel separation, and stereo synthesis, making it suitable for further adjusting existing audio materials.
• Image text recognition:Images can be imported or taken, and the text in them—such as Chinese and English—can be extracted. The recognition results can be copied, exported, or converted into speech.
• Recording cue sheet:Users can import text in advance, and it will be displayed simultaneously during recording, which is useful for maintaining coherence in voiceovers, speeches, and video recordings.
• Human voice accompaniment extraction:AI can be used to extract the vocal part or the instrumental accompaniment from audio, which facilitates the creation of practice materials, the processing of song segments, and further audio production.
• Result export and sharing:The transcribed content can be exported in formats such as Word, TXT, PDF, or as subtitles; the audio can also be shared via files or links, which facilitates teamwork and the delivery of materials.