Create audio with Studio Voice

This article is for the new STQRY Builder (Beta). Using the current STQRY Builder? See Media instead.

Studio Voice turns text into spoken audio, so you can add narration to a tour without recording it. You choose from a range of voices, accents and languages.

Step 1: Start a new audio item

In Content Library > Media, click Upload media, then click Add beside Audio. Select the Studio Voice tab.

To add Studio Voice to an audio item you've already made, open it and select the same tab.

Step 2: Enter your text

Type or paste your script into Text. Write it the way you'd like it read aloud, with full stops where the voice should pause.

Step 3: Choose a voice

Under Voices, click Set default voice. Voices are grouped as Generative, Neural and Standard, and each one shows its language. Generative voices sound the most natural, Neural come next, and Standard are the most basic. Click the speaker icon beside a voice to hear a sample. Select the one you want, then click Save & Close.

To pick a different voice later, click Change.

Step 4: Save and listen

Save the item. Builder shows "The server is generating the audio." while it works. When it's done, click the play button to listen.

If you see "The server could not generate audio from this text.", check the text and try saving again.

Behaviour notes

• Edit the text or change the voice, then save, to generate the audio again.
• Pick a voice that speaks the language of your text. In another language, use the Translate button beside Text to translate your script, then choose a voice for that language.
• To use audio hosted elsewhere, select the External file tab and paste its link into Audio URL.

Next steps

• Translate media into other languages: add narration in each language your app supports.
• Edit media details: add a transcription and a thumbnail.