Audience: Teachers with Seesaw AI subscriptions
Generate Voice allows teachers to add AI-generated narration to written text in Seesaw activities without having to record their own voice. Add voice to individual text objects, multiple objects, or all eligible text across an entire canvas. Up to 20 objects can have voice generated at a time. Text-to-speech is available for all languages Seesaw Translation supports.
Generate Voice can help you:
- Support early readers by reading instructions and text content aloud.
- Support multilingual learners with narration in other languages.
- Save time creating and recording audio.
- Make activities more engaging and interactive.
How to add voice for an entire page
Generate voice for the entire page (for example, audio instructions).
- Open Audio in the [...] toolbar 3 dot menu.
- Select Generate voice.
- Enter the text you want generated.
- Select your preferred AI Voice.
- Select Generate voice.
- Preview the audio.
Add voice to text objects
You can generate voice for one text object or multiple text objects on the canvas at once.
- Select your text
- If you want to select only one object, click on it.
- If you want to select multiple specific text objects, click and drag across them.
- If you want to select all text objects, skip this step.
- Open Audio in the toolbar and select Generate voice.
-
Select Text on page for Seesaw to automatically generate voice for all eligible text objects on the canvas.
Note: You can generate voice for up to 20 objects at a time.
Generate voice in another language
Generate Voice can create audio in the language of your text. To generate narration in another language, enter or translate your text into the language you'd like students to hear.
You can also use Translate text in Creative Tools:
- Select one or more text objects.
- Open the three-dot menu.
- Select Translate text and choose a language.
- Select the translated text.
- Open Audio and select Generate voice.
- Choose a voice and generate the audio.
Generate Voice supports all languages available in Seesaw Translation, including Arabic, English, Spanish, and Portuguese.
Frequently Asked Questions
Can I edit the text after generating the voice?
Yes, but the audio won't automatically update when you change the text. Delete the existing voice, then generate new audio for the updated text.
Can I regenerate the audio?
Yes. Select Audio in the editing toolbar and delete the existing audio. Then generate the voice again. You can also choose a different voice.
Will Generate Voice automatically detect the language?
Seesaw will do its best to detect the language of your text automatically. Very short text may be more difficult to detect accurately. Text translated directly on the Seesaw canvas can be detected accurately.
Can I change the dialect to choose between US, UK, and Australian English?
Set your language preferences in your account settings and the recommended voices for that dialect will appear at the top of the list.
How can I get the best pronunciation?
Pronunciation can vary depending on the selected voice and language. Generate Voice includes additional pronunciation guidance for US, UK, and Australian English, Spanish, Portuguese, and Arabic.
If a word doesn't sound right, try generating the audio again or selecting a different voice. AI-generated speech can vary slightly between generations, including accent and pronunciation characteristics.