Txtify is a FREE and OPEN-SOURCE tool that converts audio and video into text using state-of-the-art AI models for rapid and precise transcriptions. With Txtify, you can convert your files or urls effortlessly, and it's available for self-hosting, offering you full control over your transcription process.
Txtify utilizes advanced AI models from Whisper for transcription. The including models are: Whisper Tiny, Whisper Base, Whisper Small, Whisper Medium and Whisper Large. These models are sourced from Hugging Face repository.
Below is a table summarizing the available Whisper models, their memory requirements, and their relative inference speeds. The speed and memory requirements may vary based on the available hardware.
| Size | Parameters | Multilingual model | Required VRAM | Relative speed |
|---|---|---|---|---|
| tiny | 39 M | tiny | ~1 GB | ~32x |
| base | 74 M | base | ~1 GB | ~16x |
| small | 244 M | small | ~2 GB | ~6x |
| medium | 769 M | medium | ~5 GB | ~2x |
| large | 1550 M | large | ~10 GB | ~1x |
Txtify supports transcription in the following languages: Afrikaans, Amharic, Arabic, Assamese, Azerbaijani, Belarusian, Bulgarian, Bengali, Bosnian, Catalan, Cebuano, Czech, Welsh, Danish, German, Greek, English, Spanish, Estonian, Persian, Finnish, French, Galician, Gujarati, Hebrew, Hindi, Croatian, Hungarian, Armenian, Indonesian, Icelandic, Italian, Japanese, Javanese, Georgian, Kazakh, Khmer, Kannada, Korean, Lao, Lithuanian, Latvian, Malayalam, Mongolian, Marathi, Malay, Burmese, Nepali, Dutch, Punjabi, Polish, Portuguese, Romanian, Russian, Sinhala, Slovak, Slovenian, Albanian, Serbian, Swedish, Swahili, Tamil, Telugu, Thai, Turkish, Ukrainian, Urdu, Uzbek, Vietnamese, Yiddish, Yoruba, Chinese.
Translations are supported in the following languages using DeepL: Arabic, Bulgarian, Czech, Danish, German, Greek, English, English (British), English (American), Spanish, Estonian, Finnish, French, Hungarian, Indonesian, Italian, Japanese, Korean, Lithuanian, Latvian, Norwegian Bokmål, Dutch, Polish, Portuguese, Portuguese (Brazilian), Portuguese (excluding Brazilian Portuguese), Romanian, Russian, Slovak, Slovenian, Swedish, Turkish, Ukrainian, Chinese (simplified).
Yes, this version has limitations. You can upload audio and video files up to 100MB. When you self-host Txtify, you can modify and run the application without these limitations, giving you full control over the transcription process.
After the window is closed, all generated files and the transcription process are automatically deleted to ensure your data privacy and security.
Yes, you can self-host Txtify with full features on your own server.
Please report them using the contact form on the contact page. We appreciate your feedback and will work to resolve any problems as quickly as possible.
If your question wasn't answered here, please use our contact page to reach out to us.
