Speech to text is an application intended for the purpose of creating subtitles for video files. The application generates automatically a transcription from a video by using speech recognition.
The subtitles are automatically timed and you are able edit the text and timing, if this is needed. We support multiple languages and you can have many subtitle tracks in a media.
Let's walkthrough how the Speech-to-Text feature works with an example video!
Speech to text can be found in the left navigation bar in the video details. Contact your contact person at Qbrick, if you can't find the feature. We can activate a trial for you or we can update your agreement.
1. Start by clicking "Speech to Text" in a video to open the feature
2. Click on the list and choose the language that is spoken in the video and click "Generate transcription"
3. The transcription will be created and you can find an estimation of the expected time
4. You can edit the transcription once it is generated. There might be a need to edit the content, since the speech recognition will be affected by the quality of the audio track and language choice.
5. Click "Create subtitle form transcription", once you are done with editing the text.
6. A subtitle track is now created and you able to see that the transcript has been timed automatically into a subtitle track.
7. You can edit the text in the subtitles and also adjust the in and out points of the video. Remember to click "update" , if you have made any changes.
8. It's possible to generate multiple subtitle tracks in different languages by choosing a translation from the list in the bottom right. The translated subtitle track will appear in the subtitle editor.
9. Once you are finished click save changes and go back to the video details
10. Now you can go and preview the video and choose the wanted subtitles by clicking on the "speech bubble"