Chuchotis

Chuchotis has been designed and hand-coded by a journalist, then heavily tested by him and many colleagues before release. It runs exclusively on your computer to preserve the recording's privacy. Nothing is sent over the internet. Chuchotis is built on powerful Whisper speech-to-text models made by OpenAI, and code implementation as Whisper.cpp lead by the great Georgi Gerganov. The application also features tools to improve the quality of your transcriptions. Those are delivered as text segments which can be listened again and edited before being copied/pasted to a website backoffice, exported to word-processors or as subtitles to video software. In case of hallucinations from the AI model, troubled segments are automatically detected and can be transcribed again. Chuchotis runs on any Apple silicon-based Mac, harnessing the power of its GPU cores, starting with only 8GB memory. It manages most common audio and video file formats and deals automatically with their internal characteristics. One more thing: The french word “Chuchotis” evokes someone whispering at your ear. Chuchotis is a synonym of privacy! Automatically recognized languages (whatever the idiom of the application) are: Afrikaans, albanian, amharic, arabic, armenian, assamese, azerbaijani, bashkir, basque, belarusian, bengali, bosnian, breton, bulgarian, 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, maori, marathi, mongolian, myanmar, nepali, norwegian, nynorsk, occitan, pashto, persian, polish, portuguese, punjabi, romanian, russian, sanskrit, serbian, shona, sindhi, sinhala, slovak, slovenian, somali, spanish, sundanese, swahili, swedish, tagalog, tajik, tamil, tatar, telugu, thai, tibetan, turkish, turkmen, ukrainian, urdu, uzbek, vietnamese, welsh, yiddish, yoruba & german swiss