Most commonly asked questions

Our credit usage is straightforward:

• Transcription & Translation: 1 credit per minute of audio/video (this includes both transcription and translation as a combined service)
• Gemini 3.1 Pro Preview: 2 credits per minute (2x) when using this transcription model
• Natural AI Dubbing: 35 credits per minute of audio/video

For example, a 10-minute video would cost:

• 10 credits for transcription and translation
• 350 credits for natural sounding AI dubbing

We support a comprehensive range of languages including:

• English (English)
• Español (Spanish)
• Français (French)
• العربية (Arabic)
• 日本語 (Japanese)
• Русский (Russian)
• Português (Portuguese)
• Deutsch (German)
• Bahasa Indonesia (Indonesian)
• اردو (Urdu)
• Türkçe (Turkish)
• 简体中文 (Chinese Simp.)
• 繁體中文 (Trad.)
• Tiếng Việt (Vietnamese)
• हिंदी (Hindi)
• বাংলা (Bengali)
• தமிழ் (Tamil)
• తెలుగు (Telugu)
• Ελληνικά (Greek)
• Shqip (Albanian)
• አማርኛ (Amharic)
• Հայերեն (Armenian)
• অসমীয়া (Assamese)
• Azərbaycan (Azerbaijani)
• Башҡортса (Bashkir)
• Euskara (Basque)
• Беларуская (Belarusian)
• Bosanski (Bosnian)
• Brezhoneg (Breton)
• Български (Bulgarian)
• ဗမာ (Burmese)
• Català (Catalan)
• Hrvatski (Croatian)
• Čeština (Czech)
• Dansk (Danish)
• Nederlands (Dutch)
• Eesti (Estonian)
• Føroyskt (Faroese)
• Suomi (Finnish)
• Galego (Galician)
• ქართული (Georgian)
• ગુજરાતી (Gujarati)
• Kreyòl ayisyen (Haitian Creole)
• Hausa (Hausa)
• ʻŌlelo Hawaiʻi (Hawaiian)
• עברית (Hebrew)
• Magyar (Hungarian)
• Íslenska (Icelandic)
• Italiano (Italian)
• Basa Jawa (Javanese)
• ಕನ್ನಡ (Kannada)
• Қазақша (Kazakh)
• ភាសាខ្មែរ (Khmer)
• 한국어 (Korean)
• ລາວ (Lao)
• Latina (Latin)
• Latviešu (Latvian)
• Lietuvių (Lithuanian)
• Lëtzebuergesch (Luxembourgish)
• Македонски (Macedonian)
• Malagasy (Malagasy)
• Bahasa Melayu (Malay)
• മലയാളം (Malayalam)
• Malti (Maltese)
• Māori (Māori)
• मराठी (Marathi)
• Moldovenesc (Moldovan)
• Монгол (Mongolian)
• नेपाली (Nepali)
• Norsk (Norwegian)
• Nynorsk (Nynorsk)
• Occitan (Occitan)
• ਪੰਜਾਬੀ (Punjabi)
• پښتو (Pashto)
• فارسی (Persian/Farsi)
• Polski (Polish)
• Română (Romanian)
• संस्कृतम् (Sanskrit)
• Српски (Serbian)
• Shona (Shona)
• سنڌي (Sindhi)
• සිංහල (Sinhalese)
• Slovenčina (Slovak)
• Slovenščina (Slovenian)
• Soomaali (Somali)
• Sunda (Sundanese)
• Kiswahili (Swahili)
• Svenska (Swedish)
• Tagalog (Filipino)
• Тоҷикӣ (Tajik)
• Татар (Tatar)
• ภาษาไทย (Thai)
• བོད་སྐད (Tibetan)
• Türkmen (Turkmen)
• Українська (Ukrainian)
• O'zbek (Uzbek)
• Cymraeg (Welsh)
• יידיש (Yiddish)
• Yorùbá (Yoruba)
• 中文 (Chinese)
• Kinyarwanda (Kinyarwanda)

Languages like English are the most accurate, typically with human levels of performance and strong recognition of specialized, domain-specific vocabulary. Voice to text accuracy varies by language. You'll get the best results in these languages shown above.

You can upload audio or video files in any format, including MKV, MP3, MP4, MOV, AVI, and more. You can also import links from popular platforms like Twitter and YouTube. Our service supports all languages and file lengths, automatically transcribing and translating into your desired language.

While we strive for high accuracy and our subtitles are usually 99% accurate, we acknowledge that AI may not always be perfect. If you encounter significant errors, please contact our support team at hello@translate.mom or reach out via support chat. In cases of system errors, your credits will be automatically refunded.

Yes, once the transcription process has started, it will complete even if you navigate away. You can find your completed tasks in your history. If an error occurs, your credits will be refunded automatically.

Permanent credits are one-time purchases that never expire. Monthly credits are included with our paid plans (200 for Starter, 600 for Plus, and 2000 for Pro) and reset at the end of each billing cycle.

For custom or enterprise use cases, please contact us at hello@translate.mom to discuss tailored solutions.

VAD detects speech in your audio or video files, filtering out silence and background noise. This feature enhances transcription clarity, especially in noisy environments.

Enabling the Experimental Model utilizes our latest AI advancements to improve accuracy, particularly for challenging audio, background noise, or specific languages and accents.

We offer multiple translation engines to provide the best results. Some languages are better supported by certain engines. Please note that not all languages are compatible with DeepL.