Matching the quality of audio from coursebooks is extremely difficult. Audio recordings from coursebooks usually includes a range of accents, speakers of different ages, and genders. If you want to create your own audio, you might record yourself and a friend using your phone, but this isn’t very helpful. Your students already get plenty of practice listening to you in class. They need help with other accents. Even if you can find other speakers to record, the audio quality is unlikely particularly good. All of this makes creating your own audio difficult for teachers.
But this has changed. Teachers can now create audio with a variety of accents with perfect sound quality. Teachers don’t need access to fancy studios or expensive microphones. They just need a computer and access to Text-to-speech AI.
Here are some reasons why language teachers might use text-to-speech AI to generate audio for their classes:
Customizable. You can create audio to match the vocabulary, grammar, or topics your students are studying.
Accents. Many text-to-speech AI tools offer different accents, exposing students to a wider variety of pronunciation.
Speed. Teachers can generate audio files quickly; faster than recording yourself or trawling YouTube for suitable conversations.
Adjustable. Text-to-speech software allows you to control the speed of speech. Audio can be slowed down to make it easier for beginners, or speeded up to challenge advanced learners.
Editable. Making changes AI generated audio is also straightforward. It’s easy to insert pauses, add or delete phrases, change the speakers, or slow down the audio.
Creating a script with AI
Turning text to speech with AI
If you’re creating audio, you’re probably going to create your own scripts first. Here are some tips for generating audio scripts.
Make it realistic.
Keep it short. What might look like a relatively short script can turn into a long listening activity.
Write scripts at the right level. Include vocabulary and grammar that you want your students to decode for meaning. Check how complex your script is before you put it into AI.
Prompt Example: Please write a short [conversation / monologue] between [description of the speakers]. They are talking about [topic]. Length: [number] words / [time] length. Please write this using spoken English conventions and include appropriate aspects of language, such as contractions.
Prompt: Please write a [short dialogue] of two teenagers talking about distance learning. Length 2 minutes Please write this using spoken English conventions and include appropriate aspects of language, such as contractions.
Text generated:
You know, distance learning? It’s... I dunno, kinda a mixed bag. Like, on one hand, it’s awesome ‘cause you can just roll outta bed, grab your laptop, and you’re good to go. No worrying about the bus being late or—ugh—those early morning alarms. And honestly? The snacks are way better at home. I mean, I can have toast and chips if I want. Who’s gonna stop me, right?
But then… I dunno, it also gets kinda lonely. Like, when you’re in class, even if the lesson’s boring, you’ve got people around, y’know? You can make faces at your friends or whisper stuff about the teacher’s PowerPoint. On Zoom, it’s just… silence. And everyone’s on mute, staring into the camera like zombies. And don’t even get me started on group projects! How are we supposed to "collaborate" when half the group won’t even turn their cameras on?*
Oh, and the tech issues? Absolute nightmare. Like, I’ll be in the middle of saying something smart—well, sorta smart—and suddenly, You’re frozen! We can’t hear you!” Or the Wi-Fi cuts out completely. It’s like, I’m trying to learn here, not play IT support! Plus, teachers act like it’s super easy to focus at home, but, like, my bed is *right there.* I’ll just be listening to a lecture, and boom—five minutes later, I’m scrolling TikTok without even realizing it.
So yeah, I guess distance learning isn’t all bad, but it’s definitely not all good, either. I kinda miss real school… but also, not *too* much, y’know?
Short Video-Using Prompt
More components created with the podcast.