Getting a Pashto video in
Drop in the video file unchanged: MP4, MOV, MKV, WEBM, AVI, M4V, 3GP or a phone screen recording. The sound track is pulled out on the server, so there is no convert-to-MP3 step, and every timestamp still matches the picture. If the video is online, paste its public link under Import from link: YouTube, Shorts, TikTok, public Vimeo, Dropbox or Google Drive share links, or a direct link to a video file. Only the audio is downloaded. Playlists and channels are refused, so queue videos one link at a time, and sign-in-only posts such as Instagram need to be downloaded and uploaded.
After processing, the draft plays in sync with the video. Click a line to hear it and correct the words in place.
Pashto letters, dialects and a rough draft
Pashto uses an Arabic-based alphabet with its own extra letters, such as ټ, ډ, ړ, ښ, ږ, څ, ځ and ڼ. The model has limited Pashto data, so expect a rough draft: some words may be written with Persian or Urdu spellings, and Pashto-specific letters can be swapped for their nearest Persian forms. It works best on slow, clear speech from one speaker.
Dialects differ noticeably. Southern speech around Kandahar and northern speech around Peshawar pronounce ښ and ږ differently, and vocabulary varies across Afghanistan and Pakistan. Speakers often switch to Dari or Persian in Afghanistan, Urdu in Pakistan, and English among the diaspora in the UK, Germany, the Gulf and North America. A video that is mostly Dari or Urdu belongs on the Persian or Urdu page.
Pashto videos people transcribe
Common uploads:
- News clips and interviews from Afghan and Pakistani channels.
- Religious talks and Friday sermons.
- Poetry recitations and landay, for a written copy.
- Family videos and messages, and your own TikTok or YouTube videos for subtitles.
Right-to-left Pashto subtitles
SRT and VTT exports are UTF-8 with the text stored right to left. YouTube shows the lines correctly. Some desktop subtitle editors place full stops and question marks at the wrong end of a line; the text is fine and displays properly once uploaded. Use a font that covers Pashto letters, such as Noto Naskh Arabic, so ښ and ږ do not show as boxes.
Tips and translation
A close microphone and audio repair for crowd or traffic noise help most. Speaker labels are available on paid plans and with a Minute Pack.
The transcript stays in Pashto. For an English reading, open the Google Translate link on the transcript, or use the AI prompt export to hand the text to ChatGPT, Claude or Gemini. For audio-only recordings, see the Pashto audio to text page.