Whisper Notes: Accurate Speech2Text Transcription With Whisper Model.

- No net required. Your data never uploaded.
- High quality on-device transcription with fast speed.
- Supports over 80+ languages.
- Supports importing audio files.

You can use it to take notes, or just send message to your friends after transcribe.

■ Why Whisper Notes?

There are already many tools based on Whisper on the market, so why did I made another one? My reasons were simple.

- First, sometimes I have a wonderful dream and want to record it when I wake up, but I'm still drowsy and typing is difficult. I wanted a tool that would allow me to quickly record my speech and transcribe it into text.
- Second, when a friend sends me a message and I need to reply at length, but I'm out on the street or eating, I wanted a tool that would allow me to quickly reply to my friend without sending a voice message.

Therefore, this product compromises between accuracy and speed: we use the largest model possible, but we don't wait for minutes to complete transcription. Normally, when you record a sentence, you only need to wait a few seconds to copy the text and reply to a message.

If you pursue ultimate accuracy (which can lead to extremely slow transcription), Whisper Notes may not be suitable for you.

■ Supported Languages:

Afrikaans, Albanian, Amharic, Arabic, Armenian, Assamese, Azerbaijani, Bangla, Bashkir, Basque, Belarusian, Bosnian, Breton, Bulgarian, Burmese, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Faroese, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Haitian Creole, Hausa, Hawaiian, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Javanese, Kannada, Kazakh, Khmer, Korean, Lao, Latin, Latvian, Lingala, Lithuanian, Luxembourgish, Macedonian, Malagasy, Malay, Malayalam, Maltese, Marathi, Mongolian, Māori, Nepali, Norwegian, Norwegian Nynorsk, Occitan, Pashto, Persian, Polish, Portuguese, Punjabi, Romanian, Russian, Sanskrit, Serbian, Shona, Sindhi, Sinhala, Slovak, Slovenian, Somali, Spanish, Swahili, Swedish, Tagalog, Tajik, Tamil, Tatar, Telugu, Thai, Tibetan, Turkish, Turkmen, Ukrainian, Urdu, Uzbek, Vietnamese, Welsh, Yiddish, Yoruba

■ Thanks

Thanks to ggerganov and his open-source project whisper.cpp on Github.