Okay, so the other day I was messing around with ElevenLabs, trying to get two different voices into one audio clip. It wasn’t as straightforward as I thought it’d be, but I figured it out, so I’m gonna walk you through what I did.
Getting Started
First things first, I opened up ElevenLabs. I already had an account and everything, so I just logged in. If you don’t have one, you’ll need to sign up, but it’s pretty easy.
Picking the First Voice
Once I was in, I went straight to the Speech Synthesis part. That’s where you can type in your text and choose the voice. I picked one of the voices I liked for the first part of my script. Let’s call it “Voice A”. I typed in the first chunk of text I wanted it to say.
Generating and Downloading
After I typed in the text for Voice A, I hit the Generate button. ElevenLabs did its thing, and then I had a little audio preview. I made sure it sounded good, then I clicked the download button to save that audio file to my computer.
Switching to the Second Voice
Now, for the second voice, “Voice B,” I went back to the Speech Synthesis settings. I selected the second voice I wanted from the list. Then, I typed in the second part of my script – the part I wanted Voice B to say.
Generating and Downloading (Again)
Just like before, I hit Generate for Voice B, listened to the preview, and downloaded the audio file once I was happy with it.
Putting It All Together
At this point,I got two different audio files.
So, I opened up my audio editing software. I use Audacity because it’s free and pretty simple. I imported both of the audio files I downloaded from ElevenLabs.
Arranging the Clips
In Audacity, I had the two audio clips on separate tracks. I just dragged the second clip (Voice B) so it started right after the first clip (Voice A) ended. You can play around with the timing and add silences if you need to, I add a very short silence between the clips.
Exporting the Final Audio
Once I had everything lined up the way I wanted, I went to File, then Export, and chose the format I wanted (usually MP3). I picked a name for the file and saved it. And that’s it! Now I had one audio file with both voices, one after the other.