Why is what I'm saying not being transcribed correctly?

On Langua, you can switch between several transcription technologies via Chat Settings.

These are the best available models for transcribing what you say. But they're not perfect, and it can be particularly hard to understand exactly what language learners are trying to say!

To maximise accuracy, we recommend not speaking in a noisy environment, and pausing the recording if you are not ready to speak (if you have 'auto-record' on).

If you're having trouble being understood, you may also want to hit pause before sending your reply so you can check it before sending, and also ensure 'auto-send' is off.

Both 'V1' and 'V2' models have an impressive ability to understand even if you switch languages half way through a sentence!

For most languages, V2 is slightly more accurate and faster at transcribing. V2 is also less likely to hallucinate, writing random things that you did not say. Hallucination can occur if there is noise or music in the background, or if you leave the recording on and do not speak, e.g. if you cough and don't say anything.

V3 does not hallucinate at all, and rather than transcribe when you've finished speaking, it does it as you speak. This means the words pop up as you speak, and it's fast. So if you like that immediate feedback, it may be worth trying. The main downsides of this model are that it's a bit buggy, isn't as good at understanding when you switch languages, and the punctuation is worse. For example, if you pause for a few seconds, it will usually add a full stop when this may not make sense. So a bit of editing can be required. V3 also doesn't work with auto-send.

Feel free to experiment and see which technology works best for you! Our team is also often experimenting with new models so that we can keep offering the best available tech over time.

Occasionally, you may find that one of the models does not transcribe what you've said at all. This is frustrating but should be very rare. However, we noticed it happen in December as AI providers have had trouble scaling their systems to keep up with demand. We do our best to help you switch provider if you experience an issue.