Chapity

You can use Chapity to translate audio from various media apps.

Voice translation for any app!

Your artificial intelligence assistant, Chapity

Using Chapity, you can translate audio from various media apps in real time and view it as subtitles.

- Chapity translates voice played in other applications you run.

- The voice translation function via a cell phone recorder is not yet supported.

Use Chapity in a variety of situations where subtitles are needed.

- When you need to translate a YouTube video without subtitles

- When you need real-time translation of news from abroad

- When you need real-time translation of overseas broadcasts

How to use the app's voice translation

1. First, log in to the app and select the app you want to translate and the translation API.

2. Press the start voice translation app and check if the subtitle screen is displayed on the screen.

3. Select the media app you want to translate (YouTube, streaming video, etc.) or the app that plays audio.

4. While the subtitles screen is not closed, press the Run Application button to run the application or switch the screen to another application.

5. When a voice is played on the app, the voice is recognized and translated.

Chapity uses Open AI's Whisper speech-to-text model to

Convert voice to text, translate using DeepL, etc., and display it as subtitles.

Supported speech-to-text API

- Whisper

- Google STT (to be supported)

Supported translation APIs

- Bate-pop GPT

- DeepL Translation

- DeepL Pro Translation

(The DeepL and DeepL Pro translation APIs require API key registration as the number of users increases.)

1 credit is deducted for every minute of voice translation running time.

Users who register for the first time receive 5 credits for free.

If you unlock the Open AI API Key registration and register the API key, you can use the translation without credit deduction.

Precautions and tips for using the application

* By touching the subtitle screen, you can move the subtitle position or end the service.

*As voices are recognized and translated using an artificial intelligence model, hallucinations may occur.

* Translation quality may deteriorate if multiple voices are mixed or if there is a lot of noise or static.