Skip to content

Persian transcription

Persian audio and video to text

Upload Persian (Farsi) audio or video and get a timestamped transcript in Persian script. Persian has less training data than the biggest languages, so the small model does best on clear, formal, single-speaker speech. Casual spoken Persian and the details of spacing need a proofreading pass.

Free preview: one file up to 15 minutes and 25 MB, 3 tries a day, no account needed.

Want to keep your transcripts? Create a free account

Iranian Persian, Dari and Tajik

Iranian Persian, especially standard Tehran speech, is the strongest case. Dari, spoken in Afghanistan, has different pronunciation and vocabulary and is usually weaker. Tajik is written in Cyrillic and is not what this page produces. Spoken colloquial Persian (محاوره) differs from the written style, so the text may mix the two spellings.

Right-to-left text, ZWNJ and letters

Persian is written right to left in the Arabic-based script. The half-space (ZWNJ) is easy to lose, so words like می‌خواهم may appear joined or split. Check that ی and ک are the Persian forms, not Arabic ي and ك. Short vowels are not written, and numbers or English words can shift the order.

What speakers of Persian use it for

Recorded university lectures, interviews and oral-history recordings, podcasts and sermons, meeting notes, and captions for YouTube or Instagram video. Families transcribe voice messages to keep and search them. Writers and researchers working with Persian-language sources use transcripts to quote accurately and to search long interviews for a name or date.

Which model works best for Persian

Persian is a lower-resource language for Whisper-family models, and the small model is noticeably less reliable here than for the major languages. Use clear, single-speaker audio, keep clips short, and plan to edit a good deal. For the best result, self-hosting with large-v3 helps.

On tryscriptorium.com the no-account preview and regular accounts run the small model (the larger medium and large-v3 models run when you self-host Scriptorium). In an account, pick Small in the model menu rather than Auto: Auto prefers the fastest, least accurate model for long files or a busy queue.

Persian is a weaker language for the small model, with more wrong words in colloquial speech, music or overlap. Use short clips of one speaker, and proofread names, loanwords and ZWNJ spacing. For anything long or formal, self-host with large-v3 for a better draft.

Subtitles and captions in Persian

Persian subtitles are right to left, so test the exported file in your player, since punctuation can jump to the wrong side when Latin letters or digits appear in a line. Keep lines to about 35 to 42 characters and break at natural phrases. SRT and VTT are UTF-8, so the script displays correctly in VLC and YouTube.

The uploader is set to Persian

The upload box on this page transcribes as Persian, so the recogniser does not have to guess the language from the first seconds. If the recording is in another language or switches languages, use Audio to text, which detects the language automatically. Automatic transcription is a draft and no accuracy figure is promised: check names, numbers and anything you will rely on.

How it works

  1. Add a recording

    Drop in a video or audio file, choose one from your device, or record from the microphone. Nothing to install.

  2. It transcribes

    Speech becomes timestamped text, with speaker labels when more than one person talks.

  3. Read, fix, export

    Click any line to correct it, then download TXT, subtitles, Markdown, JSON or CSV.

Questions

Why do the spaces in some words look wrong?
Persian uses a half-space (ZWNJ) inside many words, and it is easy to lose in speech recognition. Fix it in the line editor, or run a find and replace on the exported text for words you see often.
Does it transcribe Dari or Afghan Persian?
It understands Dari more weakly than Iranian Persian, and Tajik in Cyrillic is not supported. Expect more corrections, and use clean audio. Self-hosting with a larger model may help.
Will punctuation and numbers appear in the right order?
Persian text itself is right to left, but English words, digits and punctuation can display in an odd order depending on the app. The stored text is correct, so check it in a right-to-left aware editor.
Which file types can I upload?
Video: MP4, MOV, MKV, WebM, AVI, M4V, WMV, FLV, MPEG, 3GP, TS. Audio: MP3, WAV, M4A, AAC, FLAC, OGG, Opus, WMA, AIFF, AMR, CAF. Anything else the server can decode as audio or video generally works too; there is no need to convert first.
Is it free?
Yes — one file up to 15 minutes and 25 MB with no account, up to 3 tries a day. A free account keeps your transcripts in a library and lifts the guest limits; the current limits and paid plans are on the pricing page.

Want your transcripts saved and longer files? Create a free account · See pricing · All use cases

Try it with your file

No account needed for a first transcript.