How-to guide

Text-to-Speech

2 min read Updated Jun 2026 11 steps

The text-to-speech functionality in the platform allows you to convert written text into clear, natural-sounding audio.

Using Text-to-Speech

Open a Stop: Start by opening a stop within your existing or new tour. This is where you will use the text-to-speech functionality.
Fill in the Script Field: In the “script” field, add the desired text. This can range from a few sentences to a more extensive text with a maximum of 1000 words (you’ll see a warning from 800 words). Ensure that the text is clear and well-structured for the best results.
Choose “Text to Speech” under Audio: Under the “audio file” section, select the “text to speech” option.

The Audio file section — choose between Upload File and Text to Speech.

Select a Voice: Click the voice dropdown to browse available voices, categorized by gender (male, female, neutral). Not all languages have multiple voices per gender.

Voice dropdown — choose from voices like Bella, Lily, Ollie HD, Ryan, and more.

Generate the audio: After selecting a voice, click Generate Text to Speech to create the audio file.

Voice selected (Matilda) — click Generate Text to Speech to create the audio.

Preview: Click the play button to hear the generated audio. If the result is not satisfactory, adjust the script and regenerate.

Generated audio ready for preview — 0:35 duration with playback controls.

Choose a Clear and Natural Writing Style: For optimal results with text-to-speech, use clear and natural language. Avoid complex sentences and jargon that may be difficult to pronounce or understand. This ensures a smoother and more understandable speech output.
Use Pauses and Intonation: Utilize punctuation such as commas and periods to create natural pauses in speech. This helps make the text more understandable and gives a more human rhythm to the speech. Intonation marks can also assist in conveying the correct emphasis and emotion.
Select the Right Voice: Choose a voice that aligns with the atmosphere and purpose of your tour. Different voices can convey different emotions and characters.
Adjust Spelling on a Word Basis: Use phonetic spelling to adjust the pronunciation of difficult-to-pronounce or unusual words. This helps text-to-speech systems pronounce these words correctly.
Test and Revise: Always listen to a preview of the text-to-speech output before publishing. This gives you the opportunity to identify and adjust any unnatural-sounding sentences or words. Feedback from colleagues or test users can also be valuable in improving the overall quality and effectiveness of the speech output.

Was this article helpful?