Pexo
Pexo/Blog/AI Video Use Cases/How to Add Text to Speech on Google Slides

How to Add Text to Speech on Google Slides

Lan He avatarLan He
·Last updated Nov 18, 2026
Summarize with:ChatGPTChatGPTPerplexityPerplexityClaudeClaudeGeminiGeminiGrokGrok
How to Add Text to Speech on Google Slides
Summary

Create per-slide narration with ElevenLabs, insert MP3 or WAV files through Google Drive, and check pronunciation and student access.

Make AI videos just by chatting.

To add text to speech on Google Slides, create narration as an MP3 or WAV file, upload it to Google Drive, and insert it into the relevant slide. A short plant lesson shows how to prepare a diagram and its narration before assembling the deck. You will create one short recording per slide, check scientific pronunciations, and verify that students can hear the finished lesson.

The distinction matters: hearing slide content through a screen reader and adding a reusable narration track are different tasks. Choose the workflow below when students need audio inside a shared presentation.

Choose narration or a screen reader first

Google documents screen reader support for Slides, including speech and braille output. This helps an individual navigate and read content with assistive technology; turning it on does not create a downloadable narration file for the class.

For that personal reading workflow, open Tools → Accessibility settings, enable screen reader support, and follow Google's guidance for your screen reader. Keep this separate from producing lesson audio.

For a distributable track, follow Google's documented audio insertion workflow: Slides accepts MP3 and WAV files stored in Drive. The method below supplies that file rather than relying on an assumed built-in “convert slide to speech” button.

Before You Start: What You Need

Prepare a presentation you can edit, a Google Drive location for its audio, and access to your approved audio creation service. Check your school's approved-services policy before sending lesson material to an external service. Use a generic lesson script rather than student names, assessment results, or personal information.

Also prepare a written transcript, a list of subject terms, and a naming pattern such as s01-energy-v1.mp3. Decide who will receive the presentation: one class, colleagues, or families. That audience determines which accounts need access to the audio files.

Choose a voice you are permitted to use and check the service's applicable terms for your intended distribution. Keep the original script and approved audio together.

Step-by-Step Guide to Adding Text to Speech

Step 1: Prepare the Plant Image and Its Narration Script

Prepare the plant lesson illustration in Pexo before writing narration that points to parts of it. Request a simple plant with visible roots, an enlarged leaf inset and room for arrows showing sunlight, water and carbon dioxide. Keep the background plain and add labels yourself in Slides.

Check the roots, leaf inset and arrow meanings against your curriculum reference. Request corrections to misplaced arrows or crowded details, then save the approved version. Use Insert → Image → Upload from computer to place it in Slides. The diagram should show only structures the class has learned to identify.

Write one objective and a separate narration script for each slide. For the approved plant diagram, a first script might be:

Plants use light energy to make sugars through photosynthesis. In the leaf inset, the green structures are chloroplasts. Follow the arrow from sunlight to the leaf. Which input comes from the air? Pause the presentation and write your answer before continuing.

Describe what the diagram actually contains. If chloroplasts are absent or unclear, revise the image or the sentence before generating speech. Keep editing directions outside the spoken script and retain a readable transcript. Use separate files for the introduction, explanation and practice question so later changes affect only the matching slide.

Step 2: Produce and Review One Speech Sample

Give Pexo the approved script and request the actual lesson audio: “Create a clear spoken explanation for this plant slide. Read the script at a measured pace, pronounce photosynthesis and chloroplast carefully, and pause before the question. Do not add music.” Listen to the entire result while viewing the slide. Ask for a pronunciation or pacing correction, then review the revised sample. Request a usable audio file and check the delivered format; it must be MP3 or WAV for the Slides insertion route below. Do not assume the file type from the fact that playback works in a preview.

For a documented alternative export path, sign in to ElevenLabs and open Text to Speech. Paste the first slide's script, select a permitted voice and generate a sample. Check this sample before producing the other slides.

Whichever service you use, check whether the question is distinct from the explanation and unfamiliar vocabulary is easy to hear. Keep delivery consistent across slides and leave the spoken explanation free of background music.

Step 3: Fix terminology and download the audio

Check photosynthesis, chloroplast, and any abbreviations before generating the other slides. Keep standard spelling in student-facing text. If a word sounds wrong, try a separate speech-only spelling, listen again, and retain the version that matches your instructional pronunciation.

Test pronunciation changes in a complete sentence and confirm them against your curriculum reference; a speech-only spelling may change the surrounding emphasis.

For the ElevenLabs route, after approval, open the generation's download control. The ElevenLabs download documentation also describes retrieving previous generations through Text to Speech → History, where MP3 and WAV downloads are available. Choose MP3 for this example, then rename it to match the slide.

Step 4: Upload each approved file to Google Drive

In Drive, open the lesson's audio folder and choose New → File upload. Select the downloaded audio files and wait for the uploads to finish.

Before returning to Slides, play each file from Drive. Match its opening sentence to the intended slide and confirm that the ending is complete. An approved download is useful only if you upload the correct take.

Keep a small inventory with slide number, filename, script version, and approval date.

Step 5: Insert the matching narration into each slide

Open the presentation on a computer, select the relevant slide, and choose Insert → Audio. Select its Drive audio file, then choose Select. Repeat with the matching file on each narrated slide, following Google's audio insertion guidance linked above.

Keep the audio control in a consistent, discoverable position. A short visible instruction such as “Play narration, then answer the question” helps students understand the intended sequence. Do not obscure a diagram label with the control.

Rehearse playback and slide changes in presentation mode. For independent practice, favor a design in which students deliberately play the explanation and advance when ready. Verify the resulting sequence after changing playback settings.

Step 6: Check student access and classroom playback

Share the deck with the intended people or group, and review any access-checker suggestions for linked media. Confirm only permission changes that match the intended audience.

Then ask a colleague with the same access level as a student to open the deck and play every narration file. An owner-account test cannot establish what students can hear. Test on the browser and device type the class normally uses, including headphones when appropriate.

Finally, rehearse the activity: play the plant explanation, stop for the question, and continue. Confirm that the spoken question, diagram, and written transcript agree. Keep the transcript available if audio cannot play during the lesson.

Common mistakes and how to fix them

The deck opens, but audio is unavailable. Check the media file's access for the actual audience. Do not assume presentation access proves that every linked asset is accessible. Retest after a permission change.

The voice pronounces a key term incorrectly. Return to the speech script, correct the pronunciation approach, and regenerate only that slide. Recheck the replacement before distributing the updated lesson.

The narration reads editing notes aloud. Remove directions such as “point here” or “wait five seconds” from the generation input. Replace them with actual student instructions, or keep them exclusively in your planning notes.

A corrected slide still plays an old explanation. Compare the inserted file with the inventory. Version filenames and a final slide-by-slide listening pass help catch mismatches before class.

Keep the Image and Audio Versions Together

Return to the image-generation workflow when the practice slide needs a matching plant with one input omitted. Ask to preserve the layout and colors while removing only the carbon-dioxide arrow. Review the output before inserting it; an omitted arrow is a question design, not a change to plant biology.

Save the explanation image and practice variant with the matching scripts and audio filenames. If you simplify the inset for younger students, check whether the narration still refers to visible chloroplasts. Revise the image or speech together, then listen through the pair before replacing the delivered version. Keep a quiet pause for thinking after the question.

When a Different Reading Method Is More Useful

For individual read-aloud access, use Google's screen reader workflow with the student's established accessibility setup. For narration in your own voice, record and export an MP3 or WAV using an approved recording tool, then use the same Drive-and-insert route. Keep the checked plant image and transcript with either version so the spoken explanation has the same visual reference.

Conclusion

To add text to speech on Google Slides, approve one short narration, upload it, insert it and test learner access. Complete that cycle before repeating it across the deck.

Type your thoughts here...

Pexo

Create AI videos with Pexo

Turn any idea into a publish-worthy video. One sentence is all it takes.

Frequently Asked Questions (FAQ)

Does Google Slides have built-in text to speech narration?

The workflow documented here uses a separate speech service to create MP3 or WAV audio, then inserts that Drive file into Slides. Screen reader support serves individual accessibility and does not create a narration track to distribute.

Which audio formats can I insert into Google Slides?

Google documents support for MP3 and WAV files stored in Google Drive. Download a supported format from your speech service before uploading it.

Why can I hear the narration but my students cannot?

Check access to the audio file as well as the presentation. Review Google’s media access-checker suggestions and test with an account that has the same permissions as your students.

Should I generate one audio file for the whole presentation?

For a lesson students navigate themselves, one file per slide makes replay and revision easier. Keep filenames aligned with slide numbers and check each replacement against the written transcript.

Can a screen reader create an MP3 for my class?

Enabling Slides screen reader support does not create a downloadable MP3. Use an audio-export service for narration, while retaining the screen reader for a student’s individual accessibility needs.

Lan He avatar
Lan He

Meet Lan, Senior Video Producer at Pexo, with over a decade of experience turning complex creative workflows into steps anyone can follow. A hands-on video editor and motion designer, he has taught thousands of creators how to ship video without the overwhelm, and he puts dozens of creative tools through real production work each year to see which ones actually hold up. At Pexo, he writes both step-by-step tutorials and best-of tool roundups, screen-recording each workflow himself and ranking tools on what they deliver in a real project rather than on their feature lists.

Pexo Recommend