TutorialsCaptions Mode: 150MB + Language Expansion
Product Updates6 min read

Captions Mode: 150MB + Language Expansion

Subtitles/Captions mode now supports 150MB uploads and auto language detection for a large set of languages. This guide covers exactly what changed, what is supported, and the difference between captions and English-only TTS.

🚀 What changed in this release

This update improves Subtitles/Captions mode in two big ways:

  • Upload limit increased from 100MB to 150MB for captions source media.
  • Auto language detection now supports a large multilingual set for caption generation.
This release is focused on captions workflows. TTS output remains English-only.

📦 150MB upload limit (Subtitles/Captions mode)

Captions source uploads now allow files up to 150MB in Subtitles/Captions mode. This helps with higher quality source clips and fewer compression compromises.

If you still see an old 100MB message, refresh and retry with the latest build, then upload again.

🧠 Auto language detection behavior

Captions mode now auto-detects spoken language from your source media and uses that for subtitle extraction. You do not need to manually pick a language for normal usage.

Detection quality is best with clear speech, low background noise, and a single dominant language.

🌐 Supported languages (captions mode)

The following languages are currently supported for captions auto-detection and subtitle generation:

Afrikaans
Albanian
Amharic
Arabic
Armenian
Assamese
Azerbaijani
Basque
Bashkir
Belarusian
Bengali
Bosnian
Breton
Bulgarian
Cantonese
Catalan
Chinese
Croatian
Czech
Danish
Dutch
English
Estonian
Faroese
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
Nynorsk
Occitan
Pashto
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

⚠️ Captions vs TTS (important)

Captions mode and TTS generation are different systems:

  • Captions mode: multilingual detection and subtitle output from source media.
  • TTS generation: currently English-only output voice generation.

If your workflow requires non-English subtitles, use captions mode with your original spoken audio.

✅ Best practices for reliable detection

  • Prefer one dominant speaker and reduce overlapping voices.
  • Trim long silent intros and outros before upload when possible.
  • Use cleaner source audio over heavily processed social reposts.
  • Avoid rapidly switching between multiple languages in a short segment.

Ready to put this into practice?

Open the generator, set your brand colors first, and hit Generate.

Start generating →
Captions Mode: 150MB + Language Expansion Tutorial | Sleepy Motion