Description of App
App Store description: Currently only available in English and Italian! A voice aloud reader, completely offline on your device. No internet required, no limits, no subscriptions. Just listen to that long wall of text that you really need to read or save it for later, with the voice you want. What is Koro about: TEXT TO SPEECH: - Unlimited speech synthesis: turn text of any length into spoken language, whenever you need. Simulate interesting podcasts or relaxing audiobook. - Mix and match voices: choose from built-in voices or blend them together to create your own unique sound. Make it sound just right for you. - Text import: drop in text files or PDFs and Koro will read them out loud. Great for articles, documents, or anything you want to listen to. - Share your audio: save speeches as audio files and share them anywhere. Listen back anytime, even without the app. - Advanced Customization: if some words don’t sound right, add their pronunciation at phoneme level for a perfect speech. TRANSCRIPTION (English): - Live transcription with Whisper. - Extract speech from video and audio files. SUMMARIZATION: - Summarize text with a local language model. - Long text summarization and rewriting. Privacy first: Everything happens right on your device. No cloud services, no data usage, no restrictions. Since everything works offline, your text never leaves your phone. Complete privacy. Performance: The speed and general performances of Koro change depending on your device model. Supported languages: English (American and British) and Italian. Transcription is supported in English. For questions: [email protected]
Comments
Can you use the voices outside the app?
Can the voices be used as VoiceOver or system voices?
Apple system voices
Hello, as far as I know, Apple still doesn’t allow third-party TTS to be used as the system TTS for VoiceOver. When it comes to using the voices outside the app, the only option is to export the audio file generated within the app.
nah, you can get 3rd party voices.
They do though. there's an api and everything I think. espeak is a great example, I have personal experience given I use it as my daily driver.