Text-to-speech turns text you type into a narrated audio file you can use anywhere audio is used — an audio activity, an intro, an expert tip. It's generated with AI voices, so you don't need a microphone or a recording session.
Text-to-speech is in beta, and it's switched on per organization. If you can see a Text-to-speech tab in the media library, you have it.
Generate audio
Open your media library, or the media picker inside an experience.
Switch to the Text-to-speech tab.
In the box that says Enter the text you want to convert to speech, enter or paste your script. It can be up to 5,000 characters, and the count is shown as you type.
On the Settings tab, choose a voice from the Voice list.
Click Generate preview.
When it's ready, a preview player appears so you can listen before you commit to anything.
Choose a voice
Voices are grouped by accent, each one listed with its name and whether it reads as male or female. To hear a voice before you generate your script, choose it in the Voice list on the Settings tab, and then click Sample.
Fine-tune the delivery
On the Settings tab, Speed sets how fast the voice reads. The usable range is fairly narrow, and the ends of the slider start to sound unnatural.
Under Advanced settings, you can shape more of how the voice performs your text:
Stability — lower is more expressive and more variable between takes, higher is flatter and more consistent.
Similarity — how closely the output sticks to the original voice.
Style Exaggeration — how much the voice leans into the emotion it reads in your text.
Speaker boost — sharpens the resemblance to the source voice.
To put a slider back to its default, double-click it.
If you leave these settings alone, you get a natural read. Change them when a specific line doesn't sound right, not before your first attempt.
Name and save
After you've generated something, enter an Audio name. This is what it will be called in your media library, so it's worth being specific. A name is suggested for you automatically based on the script; edit it if it isn't right.
To keep it, click Add to media library. Until you do, the audio is only a preview.
Try several versions
Generating again doesn't throw away what you had. The History tab keeps the previews you've made, so you can switch between two readings of the same line and pick the better one. Select one in History to put its text, voice and name back into the form. It's the fastest way to make a small change to something you nearly liked.
To empty everything and start again, click Clear form, under the Text-to-speech heading.
Things worth knowing
Generating audio uses your organization's AI credits.
Punctuation does a lot of work. Commas and periods are how you control pacing — a script written as one long sentence will be read as one long sentence.
After the audio is in your media library, it behaves like any other audio file. You can add it to an audio activity, add subtitles to it, and manage it in the library. See Manage media content.