97 languages, plus specialized models for the hard ones
Gaston transcribes speech in 97 languages and detects the language automatically. Where general-purpose models struggle, we train our own.
Models we train ourselves
General speech models learn mostly from widely spoken languages. For languages they handle poorly, we fine-tune dedicated models on carefully collected speech and measure them on public test sets.
Fine-tuned on about 1,060 hours of Amharic speech across five dialect regions, read and spontaneous, including phone-quality audio.
We are training more specialized models. Is there a language you need? Let us know.
Contact usEvery language Gaston transcribes
Upload a file or paste a link in any of these languages. Once transcribed, you can translate, search and export it like anything else in Gaston.
-
Afrikaans
-
Albanian
- Amharic Specialized
-
Arabic
-
Armenian
-
Assamese
-
Azerbaijani
-
Bashkir
-
Basque
-
Belarusian
-
Bengali
-
Bosnian
-
Breton
-
Bulgarian
-
Catalan
-
Chinese
-
Croatian
-
Czech
-
Danish
-
Dutch
-
English
-
Estonian
-
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
-
Norwegian Nynorsk
-
Occitan
-
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
No language matches your search. Contact us
Start transcribing in your language
Upload a file or paste a YouTube link, and Gaston does the rest.
Create an account