Languages
Accurate in 90+ languages.
Senseloom detects the language of every recording and transcribes it with world class speech AI. Here is how accurate it is in each language, measured as word error rate: the share of words a transcript gets wrong.
Word error rate up to 5%
Excellent accuracy
36 languages
- Belarusian
- Bosnian
- Bulgarian
- Catalan
- Croatian
- Czech
- Danish
- Dutch
- English
- Estonian
- Finnish
- French
- Galician
- German
- Greek
- Hungarian
- Icelandic
- Indonesian
- Italian
- Japanese
- Kannada
- Latvian
- Macedonian
- Malay
- Malayalam
- Norwegian
- Polish
- Portuguese
- Romanian
- Russian
- Slovak
- Spanish
- Swedish
- Turkish
- Ukrainian
- Vietnamese
Word error rate 5 to 10%
High accuracy
21 languages
- Armenian
- Azerbaijani
- Bengali
- Cantonese
- Filipino
- Georgian
- Gujarati
- Hindi
- Kazakh
- Lithuanian
- Maltese
- Mandarin
- Marathi
- Nepali
- Odia
- Persian
- Serbian
- Slovenian
- Swahili
- Tamil
- Telugu
Word error rate 10 to 20%
Good accuracy
18 languages
- Afrikaans
- Arabic
- Assamese
- Asturian
- Burmese
- Hausa
- Hebrew
- Javanese
- Korean
- Kyrgyz
- Luxembourgish
- Māori
- Occitan
- Punjabi
- Tajik
- Thai
- Uzbek
- Welsh
Word error rate 25 to 50%
Moderate accuracy
19 languages
- Amharic
- Ganda
- Igbo
- Irish
- Khmer
- Kurdish
- Lao
- Mongolian
- Northern Sotho
- Pashto
- Shona
- Sindhi
- Sinhala
- Somali
- Urdu
- Wolof
- Xhosa
- Yoruba
- Zulu
Accuracy is measured on public benchmarks by our speech AI provider. On your own recordings it also depends on audio quality, accents and background noise.
Turn your next call into next steps.
Upload your first recordings and get summaries, next steps and a searchable library in minutes.
Start 14 day free trial