Transcribing Persian meetings: what actually works in 2026

The short answer

1. Noter AI — Persian sits inside 60+ transcription languages with automatic language identification running on every recording, so nothing is chosen before you press record. It handles Persian meetings that switch into English, records in-person meetings from a phone, and can give you the summary and action items in English or Arabic.

2. Fireflies.ai — Persian within 100+ languages with auto-detection. The broadest published catalogue here, but AI summaries are rationed by monthly credits and pricing is per seat.

3. Notta — 58 languages with a useful bilingual side-by-side view, held back by having no automatic detection: you commit to a language before the meeting starts. Check Persian is on the current list before paying.

4. Fathom — 38 languages and the most generous free plan in the category; online calls only, and Persian sits at the edge of that list.

5. tl;dv — claims 30+ languages; strong sales analytics; weak iOS app.

6. Granola — claims 30+ languages; its phone apps record a room, but a video call still needs the Mac.

7. Otter.ai — no Persian at all. Its six languages are English (US and UK), Spanish, French, German, Japanese, and Chinese Simplified. For Persian meetings it is simply not an option.

Why Persian breaks transcripts in a specific way

• Spoken Persian is not written Persian. Vowels shift and verb endings contract in ordinary speech: "miravam" becomes "miram", "ast" becomes "e", "barayeh" becomes "vase". A model trained on books returns the formal form, which is technically correct and factually not what anyone said — a problem if the transcript is a record of who committed to what.
• Persian script is not Arabic script. Persian adds پ، چ، ژ، گ and uses ک and ی where Arabic uses ك and ي. Tools that route Persian through an Arabic model return text that is subtly wrong throughout, and Persian readers notice immediately.
• Short vowels aren't written at all. Persian, like Arabic, omits short vowels, so the same letters can spell different words. Context has to resolve them, and a weak model resolves them wrong in exactly the technical vocabulary you care about.
• The ezâfe is invisible and load-bearing. The linking vowel that joins a noun to its modifier is usually unwritten. Get it wrong and "the company's manager" and "the manager, the company" become the same string.
• Direction breaks when English is mixed in. Persian runs right to left; product names, numbers and dates run left to right. Tools that mishandle bidirectional text scramble the position of exactly the details people check. Test five minutes of your own audio before subscribing to anything on this page — that applies to every app here.

All 7 apps compared

#1 — Noter AI

Noter AI is the app this site is about, so weigh this section accordingly — the reasons it fits Persian work are concrete.

Nothing to set before recording. Transcription runs on Soniox's unified speech model with automatic language identification enabled on every recording. There is no Persian/English selector to get wrong before a meeting you didn't plan.

Persian-English mixing survives. Language is tagged word by word rather than fixed for the whole recording, so "in proposal ro ta jomeh mifrestam" comes back with the English written in Latin letters and the Persian in Persian script, instead of the borrowed words arriving spelled out phonetically.

Right-to-left text is handled properly, not patched. The app is built for right-to-left languages — Arabic is a first-class output language and the interface itself flips — so a Persian transcript containing English product names and numbers stays readable rather than scrambling.

It records the room. Supplier meetings, family business discussions, consultations, meetings in a Tehran or Dubai office, and interviews with the Iranian and Afghan diaspora — most of these are not scheduled video calls. Noter records them from a phone with one tap, a Control Center widget, or Siri, and keeps recording in the background. For virtual meetings a bot joins Zoom, Microsoft Teams, Google Meet, and Webex.

Persian in, English out. The executive summary, detailed analysis, and action items can be read in English or Arabic rather than only the raw transcript — useful when the meeting is in Persian but the report goes elsewhere.

One flat price. $9.99/month or $49.99/year covers transcription, translation, summaries, and action items, with no per-seat fees and no monthly AI credits. Rated 4.8★ on the App Store.

The honest limits. Persian is a transcription language, not yet one of the 18 output languages — so a Persian meeting can come back summarised in English or Arabic, but an English meeting cannot come back summarised in Persian. Dari and Tajik varieties are also less reliable than Tehrani Persian. There's no web or desktop app, no CRM integrations, and no permanent free tier, though roughly five minutes of your own audio can be tested free before paying.

#2 — Fireflies: broadest catalogue, metered summaries

Fireflies covers Persian inside 100+ languages with automatic detection, so it doesn't force a choice before recording and copes with English borrowings. For a company running on Zoom or Teams, with 50+ integrations to push notes into a CRM, it's a legitimate option.

Why it isn't first: in-person recording sits in a mobile app that's the thinner half of a bot-and-browser product, its AI summaries are rationed by monthly credits even on paid plans, and pricing is per seat. See the Fireflies comparison.

#3–#6 — the rest

Notta publishes 58 languages and its bilingual side-by-side transcript is genuinely useful if you produce Persian-English documents. Two blockers: there's no automatic language detection — you pick before recording — plus a three-minute cap on free sessions. Confirm Persian is on the live list before subscribing. See the Notta comparison.

Fathom publishes 38 languages and has the best free plan in the category, but it records online calls only and can't import an audio file, which rules out most in-person Persian meetings. See the Fathom comparison.

tl;dv claims 30+ languages and is strong on sales-call analytics. Its iOS app sits around 2★ and its free plan caps you at 10 AI summaries for the lifetime of the account. See the tl;dv comparison.

Granola claims 30+ languages and captures Mac system audio with no bot in the call, and its phone apps record a meeting held in a room; a video call still has to be captured on the Mac. See the Granola comparison.

#7 — Otter.ai doesn't support Persian

This gets its own section because Otter is the most recognised name in the category, and people reasonably assume a language with over 100 million speakers is covered. It isn't.

Otter supports six languages: English (US and UK), Spanish, French, German, Japanese, and Chinese Simplified. No Persian, no automatic detection, no translated summaries, and no proper right-to-left handling. Its live English transcription is the best in the category and none of that helps here. See the Otter.ai comparison.

Getting a cleaner Persian transcript

1. 1Record five minutes of a real meeting first and check the register. If casual speech comes back as formal book Persian, the model is normalising your meeting into something nobody said.
2. 2Check the letters, not just the words. Persian پ چ ژ گ and the Persian forms of ک and ی should appear. Arabic equivalents mean the tool is routing you through an Arabic model.
3. 3Put the phone flat in the middle of the table, nothing covering the mic. Contracted verb endings are short and lost first to background noise, and that's where commitments live.
4. 4Don't ask people to speak formally. With an auto-detecting tool it isn't needed, and it produces a test that doesn't match your real meetings.
5. 5Say names, dates and amounts clearly once, early in the meeting — that's where the rest of your correction time goes, especially where Persian and Latin script sit side by side.

Bottom line

For Persian, three things decide it: whether the app supports the language at all, whether it returns what was actually spoken rather than a formal rewrite, and whether it can record a meeting that isn't on a call.

Otter fails the first outright. Fireflies clears the first and records a room only from its mobile app. Notta makes you commit to a language before the meeting shows its hand. Noter AI clears all three — automatic detection with word-level language tagging, proper right-to-left handling, in-person recording from a phone, and English or Arabic summaries from a Persian meeting — at $9.99/month or $49.99/year. Test it on five minutes of your own audio, and read for register.