Formats and languages
Audio and video formats
Section titled “Audio and video formats”Audiotext extracts the audio of video files with FFmpeg, so it transcribes both.
Audio: .aac, .flac, .mp3, .mpeg, .oga, .ogg, .opus, .wav, .wma
Video: .3g2, .3gp, .3gp2, .3gpp, .3gpp2, .asf, .avi, .f4a, .f4b, .f4v, .flv, .m4a, .m4b, .m4r, .m4v, .mkv, .mov, .mp4, .ogv, .ogx, .webm, .wmv
Output formats
Section titled “Output formats”| Format | Export | Folder (WhisperX) | Folder (Whisper API) | Command line |
|---|---|---|---|---|
Plain text (.txt) |
✓ | ✓ | text |
✓ |
Markdown (.md) |
✓ | ✗ | ✗ | ✓ |
Word document (.docx) |
✓ | ✗ | ✗ | ✓ |
Subtitles (.srt) |
✓ | ✓ | srt |
✓ |
Web subtitles (.vtt) |
✓ | ✓ | vtt |
✓ |
Styled subtitles (.ass) |
✓ | ✗ | ✗ | ✓ |
Table (.tsv) |
✓ | ✓ | ✗ | ✓ |
JSON (.json) |
✓ | ✓ | json, verbose_json |
✓ |
Audacity labels (.aud) |
✗ | ✓ | ✗ | WhisperX |
Video with subtitles (.mp4) |
✓ | ✗ | ✗ | ✗ |
The summary is exported by itself to .txt, .md and .docx. See Export, the Output card and the command line.
Languages of the audio
Section titled “Languages of the audio”WhisperX and the Whisper API detect the language automatically, and can transcribe these 100 languages (the Google API requires choosing it):
Afrikaans, Albanian, Amharic, Arabic, Armenian, Assamese, Azerbaijani, Bashkir, Basque, Belarusian, Bengali, Bosnian, Breton, Bulgarian, Burmese, Catalan, Chinese, Chinese (Cantonese), 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, Nepali, Norwegian, 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 and Yoruba.
The quality depends on the language: it’s best for widely spoken languages, such as English, Spanish, French, German, Portuguese, Italian or Japanese.
Interface languages
Section titled “Interface languages”The interface of Audiotext, and this documentation, are available in:
| Language | Language | ||
|---|---|---|---|
| Català | Catalan | Polski | Polish |
| Čeština | Czech | Português | Portuguese |
| Deutsch | German | Română | Romanian |
| English | English | Русский | Russian |
| Español | Spanish | Svenska | Swedish |
| Français | French | Türkçe | Turkish |
| Galego | Galician | Українська | Ukrainian |
| हिन्दी | Hindi | Tiếng Việt | Vietnamese |
| Bahasa Indonesia | Indonesian | 简体中文 | Simplified Chinese |
| Italiano | Italian | 日本語 | Japanese |
| Nederlands | Dutch | 한국어 | Korean |
Change it in Preferences → General → Interface language. To improve a translation or add a language, see Contributing.