How to Transcribe Audio or Video to Text
Waveroom allows you not only to record audio and video podcasts and interviews. With the power of artificial intelligence, it can also turn your recordings into written words with its speech-to-text technology. Waveroom accurately transcribes what you and your guests say during your conversation and creates a text transcript that you can later use to boost your podcast SEO efforts.
Follow these steps to learn how to use the text-to-speech functionality on Waveroom and transcribe your recording, be it audio or a video conversation:
- Log in to Waveroom or create an account if you don’t have one yet.
- Select your microphone and headphones in the Devices tab under the video preview.
- Click the Start Meeting button to open your recording room. If you want to test it first, opt for Start Test Record.
- Click the Record button when you’re ready to start recording.
- When you finish, click the Stop button to end the recording.
- Wait a few seconds while the recording is saved.
- Once you see the Upload Completed notification at the bottom right corner, click the X sign to leave the meeting.
- Get back to the Room and denoise the recording first by pressing the Remove Noise icon. Speech-to-text transcription can be applied only after you denoise your recording.
- Once you remove background noise from the recording, press Make Transcription.
The transcribed recording will be marked with a notebook icon that says “transcription applied” so you can download it by pressing the downward arrow icon. Your transcription will be saved in .srt and will have time stamps along with your speech.
The .srt file is opened in a player by default. To access the transcribed recording, open the file in any text editor of your choice.
