Audio Transcription in Msty

Audio transcription allows you to transcribe your speech into prompt input using Open AI's powerful speech-to-text API. Once you have an Open AI API key, the prompt message send button will be replaced with a microphone icon. Clicking on the microphone icon will start the audio recording. After you finish speaking, the audio will be transcribed into text and sent as a prompt to the model.

At first sight the feature looks so naive and looks like speech-to-text feature available in most of the applications. But don't let the simplicity deceive you. Msty's audio transcription feature is packed with some very useful features for your audio transcription needs.

The Gorgeous Interface

As soon as you click on the microphone icon, a beautiful audio recording interface pops up. The interface is designed to be minimalistic and easy to use. It shows the audio waveform as you speak, which is a nice touch. You can also see the duration of the recording and the current transcription status.

When you are done speaking, you can click on the stop and insert button to stop the recording and insert the transcription into the prompt input. There is a play button to play the recorded audio in case you want to listen to it again before sending it for transcription. If you are not happy with the transcription, you can click on the Restart Recording button to start the recording again.

Append, Insert, or Replace

The default functionality of the audio transcription feature is, at its core, to insert the transcription into the prompt input. But Msty goes a step further by providing you with the option to append or replace the transcription. This is useful when you want to add more context to the prompt or replace the existing prompt with the transcription.

Once you already have some text in the prompt input, the send button changes to an arrow-up/send icon, which allows you to, well, send the prompt that either you have just transcribed or the one that you just typed in. This makes so that as soon as you are done speaking or typing, you can send the prompt to the model.

But if you want to append or replace or even add more to the prompt before sending it to a model, you can hold Alt key, which changes the send button back to microphone button. This will open the same gorgeous interface but now with the option to append or replace the transcription. Once you are done, you can click on the stop and insert button to insert the transcription into the prompt input at the cursor position.

The final transcription insertion is done at the cursor position at the time of clicking the stop and insert button. This means you can continue typing or speaking and then insert the transcription at the desired position once the transcription is complete. Or even select some text that you want to get replaced. The Append at the end button, however, will always append the transcription at the end of the prompt input.

Conclusion

We put in a lot of effort to make sure that this feature is easy to use and packed with useful features, while still being minimalistic and beautiful. A lot of thought went into the design and implementation of the feature, and we hope that it makes your audio transcription experience in Msty a breeze.

We are always open to feedback and suggestions, so feel free to reach out to us if you have any ideas on how we can improve Msty further, not just the audio transcription feature but the platform as a whole. We are always looking to make Msty better for you.