We support transcriptions of audio/video content in the languages listed below. For content generation, we support 50+ languages (also listed below).
Alphana Now Supports 45 Languages + Improved Transcript Accuracy
We’ve expanded our language support and upgraded our speech-to-text engine, making transcripts more accurate and reliable than ever.
Now, when uploading a video and selecting a template, you’ll see a language dropdown at the final step before generating your project. Choosing the correct language for your source video ensures the best possible transcription quality and unlocks all of Alphana’s supported languages.
Newly added or expanded languages include:
Arabic, Bulgarian, Catalan, Chinese (Mandarin – Simplified, Traditional, and Cantonese), Czech, Danish, Estonian, Finnish, Flemish, French (Canada), German (Switzerland), Greek, Hungarian, Japanese, Korean, Latvian, Lithuanian, Malay, Norwegian, Polish, Portuguese (Brazil and Portugal), Romanian, Slovak, Thai, Turkish, Vietnamese, and Multilingual (English + Spanish auto-detect).
Alphana now supports 45 languages total, including:
Arabic, Bulgarian, Catalan, Chinese (Mandarin – Simplified, Traditional, Cantonese), Czech, Danish, Dutch, English (US, UK, AU, IN), Estonian, Finnish, Flemish, French (France and Canada), German (Germany and Switzerland), Greek, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Latvian, Lithuanian, Malay, Norwegian, Polish, Portuguese (Brazil and Portugal), Romanian, Russian, Slovak, Spanish (Spain and Latin America), Swedish, Thai, Turkish, Ukrainian, Vietnamese, and Multilingual (English + Spanish auto-detect).
Let us know what you create next—wherever you’re creating from!
We’re facing issues with auto-detecting some languages. For a smooth experience, we’ve updated the list to reflect the languages that work seamlessly with auto-detection. We’re working on an update to let you manually select the language for better accuracy. The solution is to select a language before generating to take advantage of all our languages. Thank you for your patience.
Audio/Video Transcription (Input) Languages
We support a wide range of languages for transcribing audio and video files, allowing you to convert spoken content into text. Here are the main languages we currently support for transcription, with more coming soon:
Available Languages
These languages work with auto-detection for smooth transcription:
Dutch
English
French
German
Hindi
Indonesian
Italian
Portuguese
Russian
Spanish
Swedish
Turkish
Ukrainian
Available Languages with Known Issues with Auto-detection:
Chinese*
Japanese*
Korean*
Important Note for Chinese, Japanese, and Korean Transcriptions
*For transcriptions in Chinese, Japanese, and Korean, text may appear as individual characters rather than whole words or sentences. This also means automatic AI clip creation is not supported for these languages. Users must manually enter start and end timestamps to create short clips.
Content Generation (Output) Languages
For generating written content, we support an even broader selection of languages—over 50 in total. This means you can create AI-generated text in any of these languages, regardless of the language used for transcription. Here’s the full list:
Albanian, Amharic, Arabic, Armenian, Bengali, Bosnian, Bulgarian, Burmese, Catalan, Chinese, Croatian, Czech, Danish, Dutch, Estonian, Finnish, French, Georgian, German, Greek, Gujarati, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Kannada, Kazakh, Korean, Latvian, Lithuanian, Macedonian, Malay, Malayalam, Marathi, Mongolian, Norwegian, Persian, Polish, Portuguese, Punjabi, Romanian, Russian, Serbian, Slovak, Slovenian, Somali, Spanish, Swahili, Swedish, Tagalog, Tamil, Telugu, Thai, Turkish, Ukrainian, Urdu, Vietnamese.
Tip for Unsupported Languages
If your video is in a language we don’t fully support yet, there’s a workaround that might help! Try uploading the video and then paste a full transcript of the dialogue into the text box. This way, the AI can still pick up on themes and generate relevant clips, even if the language isn’t directly supported for transcription.