iSpring Suite lets you create professional voiceovers for your courses right in the editor. With AI voices powered by ElevenLabs, narration sounds natural, expressive, and close to human speech. You can generate several voiceover versions, compare them, and choose the one that works best for your course.

How to create a voiceover

  1. Click Edit Narration on the iSpring Suite toolbar.

  2. Click on Text to Speech.

  3. Paste in the text you want to narrate. Click on Insert from notes to quickly add speaker notes. The text can have up to 5,000 characters.

  4. Select the language and voice. Click on the player icon to preview the voice.



  5. Click on Generate. The generated result will appear on the right.

    If you need to stop the generation process, click on Stop.

  6. Preview the generated voiceover using the player. 

    To generate several versions, repeat steps 4 and 5 with different voices. Compare the generated results on the right.

    After each generation, the number of available characters decreases.
  7. When you’re satisfied with the result, select the voiceover and click on Insert.



  8. Choose where to insert the audio clip:


    • At the current cursor position

    • At the beginning of the slide



      If you select At the beginning of the slide and keep the Adjust slide duration option enabled, the slide duration will automatically match the voiceover length.

      If the voiceover should continue across multiple slides, clear the checkbox. You can then adjust the audio duration manually.

  9. Click on Insert.

How to select a voice from recently used voices

If you use certain voices frequently, iSpring Suite moves them to the top of the list so they’re easier to access.

To see previously used voices, go to Edit Narration > Text to Speech and open the voice dropdown list.


The Recent section stores voices that have been used on the current device. Thus, users in the same account may see different recent voices.

To make voice selection easier, try voices from the Recommended section. These are selected ElevenLabs voices that work well for most use cases.


Speech pace

Move the slider to make the narration faster or slower. Then click on Generate and preview the updated result in the Recent generations section.


Speech markup

SSML markup is not supported for ElevenLabs voices.

Voice Library

The Voice Library includes over 10,000 voices in different languages.

The library is based on user-generated content. People from around the world upload voices to the platform, so most voice names and descriptions are written in English. You can still quickly find the preferred language or accent using filters.

  1. Open Edit Narration > Text-to-Speech.
  2. Click on Voice library.



  3. Browse voices by category: education, conversation, narration, advertising, entertainment, social media, or character voices. Use the Content type filter to find the needed category.



    You can also search for voices by keyword. This is useful if you’re looking for a voice with a specific style or emotional tone.



  4. Filter voices by gender, age, and language.
  5. Click on the player icon to preview a voice. Mark a voice with a star to add it to Favorites.
  6. To see only favorite voices, enable the Favorites only filter.
  7. Click on Select voice.



    Done! You can now generate voiceovers using voices from Voice Library.

Limits to Keep in Mind

  1. Text-to-speech is available if your plan includes iSpring Suite AI. 

  2. iSpring Suite users get a trial limit of 10,000 characters for 30 days per author.

  3. ElevenLabs voices have a voiceover limit of 200,000 characters every 30 days.

  4. You can generate up to 5,000 characters at a time with an ElevenLabs voice.

  5. iSpring Cloud AI and iSpring Suite AI share the same 200,000-character limit for pages and presentations. For example, if a user spends 100,000 characters on a course in Suite AI, they will have 100,000 characters left for pages.

  6. Additional characters can be purchased separately.

  7. Legacy Google TTS voices support up to 4,000 characters per generation and up to 1,000,000 characters every 30 days.

  8. The number of characters remaining is calculated according to the following rules:
    1. The number of characters used for the last 30 days (including the current day) is deducted from the entire limit of characters that have been allowed for the author (1 million characters).

    2. If the result is greater than zero, you can convert the remaining number of characters to speech.

    3. If the result is equal to or less than zero, you won't be able to convert text to speech but will see the data when the converting will be available again.

  9. Even if you are only 100 characters away from the limit, you can still enter up to 5,000 characters in the Convert Text to Speech function and convert them to speech. This excess will be deducted from the total in the next 30-day period.

  10. If you are using an iSpring Suite AI trial version, every author will be provided with 10,000 characters until the trial period expires. If you prolong the trial version for a few months more, however, the authors will not get a new package of characters to convert text to speech.

  11. Converting text to speech is not available in the standalone iSpring Cam Pro 9 app that is purchased without the iSpring Suite AI package.

  12. Only team members assigned with the Author role can convert text to speech. The roles are assigned to team members in the iSpring Cloud.

  13. The audio with the converted text can be sped up or slowed down, overwritten, replaced, or saved to your computer.

  14. Converting text to speech is currently functioning in a beta testing mode. If you have any questions or ideas, feel free to send an email to the iSpring technical support team.

How to use legacy Google voices

Previously, iSpring customers could only use Google Text-to-Speech (TTS) voices. These legacy voices are still available in the Voice Library and can be found by the narrator’s name.

How to replace a legacy voiceover

If you previously created a voiceover with a Google TTS voice, you can regenerate it using an ElevenLabs voice.

To change the text to be converted to speech, or select a different language, speaker, or voice profile:

  1. Click on Edit Narration.
  2. Select the audio track and click on Edit Text to Speech.



  3. Make changes in the opened window and click Update.

    Regenerate the voiceover using a new ElevenLabs voice.

Notes:

  1. Let's say you made changes to the text-to-speech clip (deleted noise, for instance), and later decided to edit the text to be converted. After the text editing is done, all changes that you made previously (noise deletion) will be lost.

  2. If you made changes to the text-to-speech clip (increased the volume, for instance) and then divided the clip into multiple fragments and edited one of the fragments, the changes that you made earlier (increased volume) will be lost only in that fragment of the clip that you edited.