{"id":582,"date":"2024-04-05T16:02:35","date_gmt":"2024-04-05T14:02:35","guid":{"rendered":"http:\/\/leonardo-labs.fr\/en\/?page_id=582"},"modified":"2025-12-04T18:52:37","modified_gmt":"2025-12-04T17:52:37","slug":"chuchotis","status":"publish","type":"page","link":"http:\/\/leonardo-labs.fr\/en\/chuchotis\/","title":{"rendered":"Chuchotis"},"content":{"rendered":"\n
Transcribe recordings in a few clicks!<\/div>\n\n\n\n

\r\n <\/i>\r\n <\/div>\r\n\r\n
\r\n <\/i>\r\n <\/div>\r\n \r\n
\"\"<\/div>

From speech to text, in a few clicks<\/h1>
Chuchotis<\/b> allies the power of artificial intelligence whisper<\/i> made by OpenAI and tools to enhance transcription quality.\r\n\r\n

Just drag n’ drop an audio or video file and start transcription. After a few minutes, speech as been transcribed into text segments that you can export to a word processor, a website or as subtitles for your videos.<\/p>\r\n

You can select a range to transcribe using the beginning and ending cursors, select transcription quality and ask its English translation if needed. You can also suggest word or expressions to help the AI transcription process.<\/p>\r\n\r\n<\/a>\r\n\r\n\r\n<\/a><\/div><\/div><\/div><\/div>

\"\"<\/div>

Correct!<\/h1>

Once the transcription is done, you can replay any segment, modify or erase it.<\/p>\n

Troubled segments have been identified. You can delete them or ask for a new transcription for these.<\/p>\n

Sentences can be merged, according to the punctuation suggested by the AI.<\/p>\n

<\/a><\/p>\n

<\/a><\/p>\n<\/div><\/div><\/div><\/div>

\"\"<\/div>

Export!<\/h1>

Chuchotis<\/em><\/strong> creates text compatible with most word processors, using DOCX and RTF file formats. Transcription can also be copied\/pasted to a Web content management system or saved as subtiles (SRT) to be used for your video footages.<\/p>\n

<\/a><\/p>\n

<\/a><\/p>\n<\/div><\/div><\/div><\/div><\/div><\/div><\/span><\/p>\n\n\n\n

\n
 <\/div>\n
 <\/div>\n

<\/p>\n\n

Chuchotis<\/strong> was created by a French journalist and developer, to translate voice into text. The application runs entirely on your computer.<\/p>\n

This guarantees the complete privacy of your recordings and their transcription into text. Nothing leaves your Mac!<\/p>\n

 <\/p>\n

Chuchotis<\/strong> is based on whisper<\/em> artificial intelligence, created by OpenAI and adapted by Georgi Gerganov. Those tools are licensed under the MIT 2.0 License.<\/p>\n

Chuchotis<\/strong> is multilingual: it recognizes hundreds of languages: the 99 officially described by OpenAI and… Swiss German*<\/p>\n

 <\/p>\n

The program accepts most audio and video formats.<\/p>\n

 <\/p>\n

In many situations, simply drag an audio or video file into the application’s main window, then click a button. Depending on the computer’s power, automatic transcription with the Large<\/em> model takes between a tenth and a quarter of the duration of the recording.<\/p>\n

 <\/p>\n

As AIs sometimes lose their way to the point of experiencing what specialists call hallucinations (repetitions of phrases or groups of phrases), Chuchotis<\/strong> has been designed to detect these troubled passages, and enable them to be transcribed. In most cases, this will eliminate these hallucinations.<\/p>\n

\n

 <\/p>\n

Once transcribed, the text is presented in segments that can be replayed or modified. Chuchotis can also reconstruct complete sentences based on the punctuation of text segments.<\/p>\n

 <\/p>\n

Transcripts can then be exported, with or without timecodes, to a word processor (Word\/Docx and RTF formats), copied to the clipboard (for pasting into a CMS) or exported as subtitles (SRT) for integration into your videos.<\/p>\n

 <\/p>\n

Important<\/strong>: the use of artificial intelligence is power-hungry. If you’re using a laptop, make sure its battery is fully charged. Better still, plug it into the mains if you can.<\/p>\n

 <\/p>\n

Multilingual recordings<\/strong>. Powerful though they may be, AIs capable of running on a PC, whether fixed or portable, do not cope well with recordings made in several different languages. If you have started a recording in one language and then switched to another which is used for the rest of the exchange, delay the start of the transcription until the main language starts. Otherwise, Chuchotis<\/strong> may translate the transcription into the first language encountered, adding translation errors to the inevitable speech recognition errors.<\/p>\n<\/div>\n

\n

 <\/p>\n

Speaker identification<\/strong>. This first version of Chuchotis<\/strong> does not detect speakers on a recording. But if the recording is of good quality, the program will be able to transcribe all the words that have been spoken.<\/p>\n

 <\/p>\n

Features<\/strong><\/p>\n

\u2022 Import of wav, mp3, mp4, m4a, aiff, aifc and caf audio files.<\/p>\n

\u2022 Import of mov, m4v, mp4 and dv video files.<\/p>\n

\u2022 Choice of transcription model: Medium<\/em> (fast but less efficient) or Large<\/em> (more efficient, but more time- and energy-intensive).<\/p>\n

\u2022 Suggestion of words or expressions likely to be incorrectly transcribed.<\/p>\n

\u2022 Provides an automatic language detection mode, or select language in the application list*.<\/p>\n

\u2022 After transcription, the text can be translated, or not, in english.<\/p>\n

\u2022 Text segments are editable, and are automatically labeled depending on their status.<\/p>\n

\u2022 Research\/remplace text in any\/all segments.<\/p>\n

\u2022 Provides a custom file format to keep a link between audio and text segments.<\/p>\n

\u2022 Fast identification of hallucinated segments or problematic ones (when text seems too short vs audio length).<\/p>\n\n

\u2022 Export to word processors, website management tools or as subtitles.<\/p>\n

\u2022 Detailed help function<\/p>\n

 <\/p>\n

Compatibility<\/strong><\/p>\n

For all Mac computers, desktop or laptop, with an M chip and a minimum of 8 GB memory. Compatible with Monterey (MacOS 12), Ventura (MacOS 13) and Sonoma (MacOS 14).<\/p>\n\n

 <\/p>\n

MacOS\u00ae is a registered trademark of Apple\u00ae.<\/p>\n

Word\u00ae is a registered trademark of Microsoft\u00ae.<\/p>\n

<\/p><\/div><\/a>\n
\n

*List of recognized languages<\/b>: 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, swiss german, tagalog, tajik, tamil, tatar, telugu, thai, tibetan, turkish, turkmen, ukrainian, urdu, uzbek, vietnamese, welsh, yiddish, yoruba<\/p><\/div>\n","protected":false},"excerpt":{"rendered":"

Transcribe recordings in a few clicks!     Chuchotis was created by a French journalist and developer, to translate voice into text. The application runs entirely on your computer. This guarantees the complete privacy of your recordings and their transcription into text. Nothing leaves your Mac!   Chuchotis is based on whisper artificial intelligence, created […]<\/p>\n","protected":false},"author":2,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_bbp_topic_count":0,"_bbp_reply_count":0,"_bbp_total_topic_count":0,"_bbp_total_reply_count":0,"_bbp_voice_count":0,"_bbp_anonymous_reply_count":0,"_bbp_topic_count_hidden":0,"_bbp_reply_count_hidden":0,"_bbp_forum_subforum_count":0},"_links":{"self":[{"href":"http:\/\/leonardo-labs.fr\/en\/wp-json\/wp\/v2\/pages\/582"}],"collection":[{"href":"http:\/\/leonardo-labs.fr\/en\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"http:\/\/leonardo-labs.fr\/en\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"http:\/\/leonardo-labs.fr\/en\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"http:\/\/leonardo-labs.fr\/en\/wp-json\/wp\/v2\/comments?post=582"}],"version-history":[{"count":21,"href":"http:\/\/leonardo-labs.fr\/en\/wp-json\/wp\/v2\/pages\/582\/revisions"}],"predecessor-version":[{"id":662,"href":"http:\/\/leonardo-labs.fr\/en\/wp-json\/wp\/v2\/pages\/582\/revisions\/662"}],"wp:attachment":[{"href":"http:\/\/leonardo-labs.fr\/en\/wp-json\/wp\/v2\/media?parent=582"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}