Make a podcast with multiple speakers

Create an episode

1. Open Podcast Studio.
2. Choose a mode: Best, Fast or Clone.
3. Write your script with a speaker tag on each line. To see how it works, click Demo conversation.
4. Choose a voice for each speaker.
5. Pick your settings, then generate.

Write the script

Start each line with a speaker tag:

[SPEAKER 1] Welcome back to the show.
[SPEAKER 2] Thanks for having me. [break 1] It's great to be here.
[SPEAKER 1] Let's start with your new project.

A podcast needs lines from at least two speakers. Use Add speaker to add another, up to the limit shown on the page.

Speaker names such as [HOST] aren't accepted. If your script has them, click Change to speaker tags to convert it. Add a pause anywhere with [break 1.5].

Choose a mode

Mode	Voices	Good for
Best	Studio voices	The best sound from our voice library
Fast	Fast voices and your blends	Longer episodes at the lowest cost
Clone	Your cloned voices	Episodes in your own voices

Best and Clone also let you choose a model. Fast has a Pace setting.

Choose voices

Each speaker needs a different voice. In Best and Fast modes, all speakers must use the same language. If you see "This model can't speak one of the voices' languages", choose another voice or model.

Settings

• Pause between lines: From 50 to 1,000 milliseconds. The default is 500.
• Format: MP3, WAV or Opus.
• Folder and Title: Keep episodes organised in My Speeches. A title can be up to 50 characters.

After you generate

Your episode runs in the background, so you can leave the page. It appears in My Speeches when it's ready.

Credits are charged when the episode is finished, and returned if it fails. The rate depends on the mode, and Fast costs the least.