This guide will walk you through the process of generating and exporting speech using NarrationBox's intuitive studio interface. You'll learn how to select a voice, generate audio from your text, and customize your export settings.
Start a New Text to Speech Project: From the NarrationBox home screen, click on the "Text to speech" option to open the studio.
Understand the Studio Interface: The studio features a text input area where you can type or paste your content. Each block of text can be assigned a different voice.
Change the Voice: To change the voice for a text block, click on the current voice name (e.g., "Harlan"). This will open the voice selection menu.
Select Your Desired Voice: Browse through the available models (e.g., Enbee V1, Enbee V2 Alpha) and voices. For this example, scroll down and select "Kate" from the Enbee V1 list, then click "Use Voice" at the bottom right.
Generate Speech: With your text and chosen voice configured, locate and click the "Generate speech" button at the bottom of the screen. The system will then process your text and create the audio.
Play Generated Speech: Once the audio generation is complete, a "Sounds amazing! Your generation is ready" notification will appear. Click the play button (right arrow) in the audio player to listen to your generated speech.
Export Your Audio: To save your speech, click the "Export" button located at the top right of the screen.
Configure Export Settings: In the "Export Audio" pop-up, choose your preferred file name, decide if you want to download it as a "Single file" or "Split by blocks", select your desired audio "Format" (e.g., MP3, WAV), and set the "Quality" (e.g., Low, Medium, High, Ultra).
Finalize Export: After configuring your settings, click "Export Speech" to download your audio.
Close Export Window: You can close the export window by clicking the 'x' icon in the top right corner to return to your project.