---
updatedAt: 2026-05-05T23:00:48.000Z
agentTools:
  projectIndex: https://docs.nanonets.com/llms.txt
---

# Languages Supported

**Nanonets supports character/word recognition in over 200+ languages including but not limited to:**

1. Acehnese
2. Acholi
3. Adangme
4. Afrikaans
5. Akan
6. Albanian
7. Algonquinian
8. Amharic
9. Ancient Greek
10. Arabic
11. Araucanian/Mapuche
12. Armenian
13. Assamese
14. Asturian
15. Athabaskan
16. Azerbaijani
17. Aymara
18. Balinese
19. Bambara
20. Bantu
21. Bashkir
22. Basque
23. Batak
24. Belarusian
25. Bemba
26. Bengali
27. Bikol
28. Bislama
29. Bosnian
30. Breton
31. Bulgarian
32. Burmese
33. Catalan
34. Cebuano
35. Chechen
36. Cherokee
37. Chinese
38. Chinese (Mandarin, Hong Kong)
39. Chinese (Mandarin, Simplified)
40. Chinese (Mandarin, Traditional)
41. Choctaw
42. Chuvash
43. Cree
44. Creek
45. Crimean Tatar
46. Croatian
47. Czech
48. Dakota
49. Danish
50. Dhivehi
51. Duala
52. Dutch
53. Dzonkha
54. Efik
55. English
56. English (British)
57. Esperanto
58. Estonian
59. Ewe
60. Faroese
61. Fijian
62. Filipino
63. Finnish
64. Fon
65. French
66. French (Canadian)
67. Fulah
68. Ga
69. Galician
70. Ganda
71. Gayo
72. Georgian
73. German
74. Gilbertese
75. Gothic
76. Greek
77. Guarani
78. Gujarati
79. Haitian Creole
80. Hausa
81. Hawaiian
82. Hebrew
83. Herero
84. Hiligaynon
85. Hindi
86. Hungarian
87. Iban
88. Icelandic
89. Igbo
90. Iloko
91. Indonesian
92. Irish
93. Italian
94. Japanese
95. Javanese
96. Kabyle
97. Kachin
98. Kalaallisut
99. Kamba
100. Kannada
101. Kanuri
102. Kara-Kalpak
103. Kazakh
104. Khmer
105. Khasi
106. Kikuyu
107. Kinyarwanda
108. Kirghiz
109. Komi
110. Kongo
111. Korean
112. Kosraean
113. Kuanyama
114. Lao
115. Latin
116. Latvian
117. Lingala
118. Lithuanian
119. Low German
120. Lozi
121. Luba-Katanga
122. Luo
123. Macedonian
124. Madurese
125. Malagasy
126. Malay
127. Malayalam
128. Maltese
129. Mandingo
130. Manx
131. Maori
132. Marathi
133. Marshallese
134. Mende
135. Middle English
136. Middle High German
137. Minangkabau
138. Mohawk
139. Mongo
140. Mongolian
141. Nahuatl
142. Navajo
143. Ndonga
144. Nepali
145. Niuean
146. North Ndebele
147. Northern Sotho
148. Norwegian
149. Nyanja
150. Nyankole
151. Nyasa Tonga
152. Nzima
153. Occitan
154. Ojibwa
155. Old English
156. Old French
157. Old High German
158. Old Norse
159. Old Provencal
160. Oriya
161. Ossetic
162. Pampanga
163. Pangasinan
164. Papiamento
165. Pashto
166. Persian
167. Polish
168. Portuguese
169. Portuguese (European)
170. Punjabi
171. Quechua
172. Romanian
173. Romansh
174. Romany
175. Rundi
176. Russian
177. Sakha
178. Samoan
179. Sango
180. Sanskrit
181. Scots
182. Scottish Gaelic
183. Serbian
184. Shona
185. Sinhala
186. Slovak
187. Slovenian
188. Songhai
189. Southern Sotho
190. Spanish
191. Spanish (Latin American)
192. Sundanese
193. Swahili
194. Swati
195. Swedish
196. Syriac
197. Tagalog
198. Tahitian
199. Tajik
200. Tamil
201. Tatar
202. Telugu
203. Temne
204. Thai
205. Tibetan
206. Tigirinya
207. Tongan
208. Tsonga
209. Tswana
210. Turkish
211. Turkmen
212. Udmurt
213. Ukrainian
214. Urdu
215. Uzbek
216. Venda
217. Vietnamese
218. Votic
219. Welsh
220. Western Frisian
221. Wolof
222. Xhosa
223. Yiddish
224. Yoruba
225. Zapotec
226. Zulu

**Can a single model support multiple different languages?**

Yes. You can build a single model to handle documents in multiple languages. It contributes to better accuracy and is easy to deploy.

**Is handwritten text supported?**

Yes, we support handwritten documents — with some important notes:

* Handwriting must be legible to the human eye. If a human reader struggles to understand the handwriting, AI models may also have difficulty extracting text reliably
* Results may vary depending on writing style, image clarity, and document structure
* We recommend testing a few samples to evaluate performance for your specific use case

Tip: Neat, well-scanned handwritten forms (e.g., block letters or clearly written fields) tend to produce better results