Languages

Farsi Audio to Text

Upload a Farsi voice note, interview or video and get a timestamped draft in Persian script. Persian is already selected in the upload box, which is the right setting for Farsi.

  • Free, no sign-up
  • No credit card
  • 90+ languages
  • TXT, DOCX, SRT, VTT, PDF

New transcription

Try one file now, no sign-up needed. A free account keeps your transcripts and lets you do more.
Auto-detected by default
Label who said what
A last resort for very noisy recordings; most files are better without it

How it works

Three steps, no setup.

  1. 01Step · 01

    Upload

    Drop an audio or video file. Choose the language and whether to label speakers.

  2. 02Step · 02

    Transcribe

    We extract the audio, transcribe it and identify speakers. Watch progress live.

  3. 03Step · 03

    Use it

    Read along with the player, jump by clicking a line, and share the transcript.

Farsi, Persian and the setting to choose

Farsi (فارسی) is what speakers call their own language. The word comes from Pars, the region in southern Iran that the Greeks called Persis, which is where the English name Persian comes from. Many people in Iran and the diaspora say Farsi even when speaking English, which is why it is often the word typed into a search box.

In the upload box the language is listed as Persian, code fa. This page preselects it, so you can upload straight away. There is no separate Farsi option, and none is needed: Farsi and Persian are the same language.

Set the language yourself rather than relying on auto-detect. A short WhatsApp or Telegram voice note, or a recording that opens with a greeting in English, gives auto-detect little to go on, and Farsi can be mistaken for Arabic or Urdu because the three share many loanwords.

Spoken Farsi versus written Farsi

Everyday Farsi, especially the Tehran variety heard in most podcasts and videos, is far from the formal written language. People say میگه (mige) where a book would write می‌گوید, or نمیدونم (nemidoonam) for نمی‌دانم. The model sometimes writes the spoken form, sometimes the formal one, and occasionally mixes both in a single paragraph.

Decide early which style you need. For subtitles and quotes, spoken forms usually read more naturally. For a report or an academic appendix, many people convert to formal written Persian while they review. Either way, pick one style and apply it through the whole transcript so readers are not distracted by switches.

Accent adds another layer. Speakers from Isfahan, Shiraz, Mashhad or Tabriz, and Azerbaijani or Kurdish speakers talking in Farsi, keep their own vowels and rhythm. The draft will still be readable, but expect more words to fix than with a Tehran newsreader.

Finglish, digits and right-to-left text

A few practical points about the text itself before you share it.

  • The transcript is in Persian script. It does not produce Finglish (Persian typed in Latin letters, like 'salam, chetori'). If you need a romanized version, paste the text into an AI assistant with the AI prompt export and ask for one, then check it.
  • Numbers may come out as Persian digits (۱۴۰۳), Western digits (1403) or words. Solar Hijri dates are written the way they were spoken, so confirm years and dates against the audio.
  • Persian is written right to left. When you paste a DOCX or TXT export into another document, set the paragraph direction to right-to-left if punctuation lands at the wrong end of a line.
  • English brand names and technical terms may appear in Latin letters or spelled out in Persian, sometimes both ways in one file.

How good is the draft

Persian has less training data behind it than the big European languages. A clear recording with one speaker gives a usable draft that still needs a careful read. Group conversations, satellite TV clips with music under the voice, and phone calls produce weaker text, and names of people and places are the most common errors.

Review with the player running. The current line is highlighted, and clicking any line plays it from that point so you can correct the word in place. For long recordings, fix the parts you plan to quote first.

Exporting and reading it in another language

Export TXT or DOCX for reading and quoting, SRT or VTT for Farsi subtitles on a video, and CSV for research coding. Timestamps can be turned on or off when you export. Speaker labels are available on paid plans or with a Minute Pack.

RocketScribe writes down the Farsi that was spoken and does not translate it. To follow it in English, use the Google Translate link on the transcript, or the AI prompt export to ask ChatGPT, Claude or Gemini for a summary or translation. Your files are never used to train AI models.

FAQ

Farsi Audio to Text: questions, answered.

Which language do I pick for Farsi?+

Persian (code fa). This page selects it for you. Farsi is the Persian name for the same language, so there is no separate option.

Can I transcribe Farsi audio for free?+

Yes. Upload a file without signing up, and create a free account if you want to keep the transcript. Free plan limits are shown in the pricing section on this page.

Will the transcript be in Finglish or Persian script?+

Persian script. There is no built-in romanization. You can ask an AI assistant for a Latin-letter version using the AI prompt export.

Why does my transcript mix spoken and formal Farsi?+

The model sometimes writes colloquial forms like میگه and sometimes the formal written form. Choose one style and make it consistent while you review.

Does it work for Telegram and WhatsApp voice notes?+

Yes. Upload the saved audio file as it is. Keep Persian selected, because short notes are where auto-detect most often guesses wrong.

Can I get English text from a Farsi recording?+

Not directly. The transcript stays in Farsi. Use the Google Translate link or the AI prompt export to read it in English.

Do I need an account?+

No. You can transcribe one file right away without signing up. A free account then gives you 3 files a day (120 minutes a month) and keeps your transcripts: the file you transcribed before signing up moves into the account.

Which formats are supported?+

Any common audio or video file: MP3, WAV, M4A, AAC, FLAC, OGG, MP4, MOV, WEBM, MKV and more. We extract the audio from video automatically.

How accurate is it?+

On clear recordings expect accuracy comparable to leading transcription services. Background noise, crosstalk and heavy accents reduce it, as they do everywhere.

Pricing

Start free. Pay only if you need more.

The Free plan needs no card. Paid plans add longer files, batch uploads and speaker identification.

Free

$0

no card required

For trying it out and the occasional file.

  • 3 files a day
  • 120 minutes a month
  • Timestamps and synced player
  • AI prompt export and translation
  • Transcripts kept for 30 days
Start free
PlusMost popular

$6/ month

billed $72 yearly

For people who transcribe every week.

  • 1,200 minutes of transcription a month
  • Speaker identification included
  • Files up to 300 minutes and 5 GB
  • Upload 20 files at once
  • Up to 5 files processed in parallel
  • Priority processing
Get Plus
Unlimited

$10/ month

billed $120 yearly

For heavy users and small teams.

  • Unlimited transcription*
  • Speaker identification, 2,400 minutes a month
  • Files up to 600 minutes and 5 GB
  • Upload 50 files at once
  • Up to 5 files processed in parallel
  • Priority processing
Get Unlimited

Minute Packs

One-timefrom $1 per 60 minutes
  • Plus limits on Free: longer files, batch uploads
  • Speaker identification
  • No RocketScribe line in your exports
  • Valid 12 months, packs stack

Top up any plan. Stackable and valid for 12 months. A pack's minutes are one shared pool for whatever your plan doesn't cover: transcription on Free and Plus, speaker identification (and transcription past fair use) on Unlimited. On Free, a pack also unlocks Plus limits, with transcription and speaker identification both drawn from it.

* Fair use: 12,000 minutes a month. Beyond that, uploads pause until the next cycle or a Minute Pack. Prices in USD.

Farsi Audio to Text

Pick a file, choose the language, press Transcribe. No sign-up needed to try.

Transcribe a file