The most important thing in a service is often not just what is said, but how it's said. Is the speaker sharing a joke? Are they speaking with serious, pastoral care? So much of the meaning is carried in the tone, timing, and emphasis of the original speaker.

When you're enclosed in a text-to-speech audio feed, you miss all of that. You're disconnected from the feeling in the room and the friendliness of the person speaking. You might get the words, but you risk missing the heart.

So it is with translation. At the moment, all translation models go via a text stage. At this current stage of technology, that process strips out the original emotion and emphasis. That stripped-out nuance can never be fully put back in by a text-to-speech engine.

We've found that a better experience for many is actually reading the translation while listening to the original speaker.

This approach gives you the best of both worlds:

This is how many people learn a new language—like reading subtitles while listening to the original audio. It's an active, engaging way to participate.

This focus on captions over audio isn't just a design choice; it's a deliberate, missional decision to make Breeze Translate accessible to everyone.

The most advanced, high-quality text-to-speech models run on powerful servers that cost a lot of money to run. Implementing them would multiply the cost of the service by four to five times.

We've also chosen to keep our technology simple and straightforward to keep costs low and make the service easy to use.

We do offer text-to-speech that runs on your device. This works very well on Android, with over 100 languages supported. However, on iOS, Apple does not make the high-quality voices available to web browsers. The only way to access them would be to build a separate, native app that you would have to download from the App Store.

This would add complexity for you, the user, and dramatically increase our development costs by forcing us to maintain multiple code bases. We'd rather keep it simple — no... apps to to download and install — and pass those savings on to you.

With all that said, text-to-speech is on our roadmap. We can see this technology coming in time, and we will be on the lookout as new technologies arrive.

In fact, we have deliberately designed our technology stack to enable us to make the most of the latest technologies. A perfect example is our recent move to a new multilingual transcription engine that will understand 60 languages without any prompting.

We are also actively investigating an option, particularly for Farsi (Persian), which we know is a language we get asked about. Our hope is to progress this over the coming months, allowing us to deliver good quality audio for this language while not increasing the cost of Breeze Translate.

See for yourself how Breeze Translate can help you build a more inclusive and integrated church family.

Click Here to Start Your Free, Flexible Trial Today