Podcastle’s text-to-speech feature is a powerful tool that allows users to convert written text into natural-sounding speech using AI-generated voices. To use text-to-speech:
Create a new project and select Generate Speech.
Paste or type up to 600 characters.
To change the AI-generated voice, select Choose Speaker from the dropdown menu.
If you have created your own digital voice, it will appear under My Voices.
To listen to a stock voice, hover the name’s initial and press the play button. Once you’ve indicated your voice selection click the +Add button.
Click Generate.
Once your audio file has generated, you can edit the spoken word by right clicking on the audio file and clicking Transcribe. Alternatively, you can toggle directly over to Text Mode.
Within text mode, you can play your recording, edit or delete the text, add a new paragraph, or change the speaker.
You can toggle back over to the audio editor to use other AI features like Magic Dust to make your audio sound amazing and then export or publish your finished project.