| I&T Solution |
Speech-to-Text AI-Based Voice and Recording Transcription Engine
(REF: S-1306) |
| Trial Project |
|
| Solution Feature |
- We provide automatic voice recognition and transcription AI model which is optimized for generating transcripts. After importing the audio files, the AI model will process and generate the required transcript within a short time period (3 minutes for an 1-hour audio file at the soonest).
- The Datax enginesupports input of verbal and written Chinese, English and Mandarin. It can translate Chinese to English or Cantonese to written Chinese and output the file in different formats, e.g. SRT file.
- We provide comprehensive tutorial videos to guide users to understand the features and functions of the service and to practically use the service step by step.
- AI supports transcribing audio automatically, and can wrap text by detecting pause in audio and will match the time period to each audio sentence.
|
| Trial Application and Expected Outcome |
- To accurately convert speech into text, and export the file as transcription formats (e.g. SRT, DOCX or TXT).
- To speed up the processing time of daily operations by reducing manual efforts to handle multiple audio messages.
- To help departments to prepare documents for daily meetings and reporting to high management.
- To generate and keep text files of recordings of daily operation including case investigation and site inspection, allowing internal departments to search and to reference relevant recording and transcripts for their daily workflow.
|
| Additional Solution Information |
Datax_STT_sep_2022_rs.pdf
|
| Info on I&T Solution Provider |
|
