Roundup

The best app for transcribing multilingual meetings in 2026

Every transcription app advertises a language count. Almost none of them tell you what happens when a meeting is actually held in two languages — when a team switches between Arabic and English mid-sentence, or when a client call runs in Spanish and the notes have to reach a Japanese head office. That's a harder problem than "how many languages do you support", and most of these apps fail it the same way: they make you pick one language before you press record. Here's how the seven main options rank on the job that matters.

Updated July 2026

The short answer

1. Noter AI — best overall for multilingual meetings. Transcription covers 60+ languages with automatic language detection, so you never choose a language before recording, and it keeps up when speakers switch language mid-conversation. It's also the only option here that can record a two-language meeting happening in a room, and that translates the *summary and action items* rather than just the raw transcript.

2. Fireflies.ai — the largest catalogue, 100+ languages with auto-detection. Strong on coverage, but online calls only and its AI summaries are rationed by monthly credits.

3. Notta — 58 languages and a genuinely useful side-by-side bilingual transcript view, held back by a significant flaw for this use case: you must select the language before recording starts.

4. Granola — best bot-free option, but Mac-first and only useful if your multilingual meetings happen at a desk.

5. Fathom — good free plan, 25+ languages, online calls only.

6. tl;dv — translated transcripts aimed at sales teams; weak mobile app.

7. Otter.ai — only 6 languages, no auto-detect. If your meeting isn't in English, Spanish, French, German, Japanese, or Chinese Simplified, Otter cannot help you at all.

One honest limit up front: Noter AI *transcribes* in 60+ languages but *translates* the finished notes into 18. If you need the output written in a language outside that 18, check the list further down before subscribing.

"Multilingual meeting" means three different things

Before comparing apps, it's worth being precise about which situation you're in — because they need different features.

  • One language, different from your reading language. The meeting is entirely in Japanese; you need the notes in English. The common case, and the easiest to solve — you need accurate transcription in the source language plus a good translation of the *output*.
  • Two languages in the same conversation. A bilingual team, or a meeting with an interpreter, where people switch language mid-sentence. This is the case that breaks most apps: if the tool locked itself to one language when you pressed record, everything spoken in the other language comes out as garbage.
  • One meeting, many readers. The call happens in English but the notes go to offices in Turkey, Brazil, and Korea. What matters is how many target languages the summary can be produced in, and whether that's included in the price or billed per seat.

All 7 apps compared

Three columns decide most real cases. Auto-detection removes the single most common way a multilingual recording gets ruined — choosing the wrong language, or forgetting to choose at all. In-person capture eliminates Fireflies, Fathom, Otter and (in practice) tl;dv outright, since they're built around a bot joining an online call and cannot hear a conversation across a table.

Translating the summary and action items is the column almost nobody talks about. Translating a 9,000-word transcript isn't that useful — nobody reads it. What you actually send onward is the summary and the list of who agreed to do what. If those stay in the original language, the translation feature hasn't solved your problem.

AppTranscription languagesAuto-detects languageTwo languages in one recordingRecords in personTranslates summary & action items
Noter AI60+Yes — always onYesYes — one tap on the phoneYes — summary, analysis and action items
Fireflies.ai100+YesYesNoTranscript only; summaries capped by credits
Notta58No — pick before recordingLimitedYes (web/mobile)Transcript only; bilingual side-by-side view
Granola30+ claimedPartialLimitedYes (Mac system audio)Partial
Fathom25+PartialLimitedNoTranscript only
tl;dv30+PartialLimitediOS only, unreliableTranscript only
Otter.ai6NoNoVia phone micNo

#1 — Noter AI

[Noter AI](https://apps.apple.com/us/app/noter-ai-meeting-note-taker/id6747296459) is the app this site is about, so weigh this section accordingly — but the reasons it tops this particular list are specific and checkable.

You never pick a language. Transcription runs on Soniox's unified speech model, which covers 60+ languages with automatic language identification switched on for every recording. There's no language selector to get wrong and no setup step before an unexpected meeting. You can optionally supply hints to bias accuracy toward the languages you expect — but they're hints, not a lock.

It keeps up when the language changes mid-conversation. Because the model tags language at the word level rather than committing to one language per recording, a meeting that runs half in Arabic and half in English comes back as one coherent transcript with both languages rendered properly — instead of the second language arriving as phonetic nonsense, which is what happens on tools that lock to a single language at record time.

It records the room. Multilingual meetings often aren't on Zoom — they're at a client's office, on a site visit, in a clinic, in a family business. Noter records in person with one tap, a Control Center widget, or Siri, and keeps recording in the background. For virtual meetings the bot joins Zoom, Microsoft Teams, Google Meet, and Webex, so both halves of your week are covered by one app.

It translates the part people actually read. After the meeting you get an executive summary, a detailed analysis, and action items with owners attached — and all of those can be read in your target language, not just the raw transcript. Record in Arabic, send a clean English summary and task list to your manager, without opening a second tool.

One price, no rationing. $9.99/month or $49.99/year covers transcription, translation, summaries, and action items. No per-seat multiplication and no monthly AI credits — which matters most for exactly the distributed international teams this page is about.

The honest limits. Translation output is capped at 18 languages (listed in the FAQ below) even though transcription covers 60+ — so an uncommon source language transcribes fine, but you may not be able to render the finished notes in it. There's also no web or desktop app, no CRM integrations, and no permanent free tier.

#2 — Fireflies.ai: the biggest catalogue

If your only question is "is my language on the list", Fireflies is the broadest option here: 100+ languages with automatic detection. For genuinely rare languages it covers ground Noter AI's 60+ does not, and detection means you don't have to choose in advance either.

Why it isn't first: it can't record anything that isn't an online call, so an in-person bilingual meeting is out of reach entirely. Its AI summaries are rationed by monthly credits even on paid plans — so in a heavy month the translated summary you need may not generate. And pricing is per seat, which compounds fastest for the multi-country teams most likely to need this. See the Fireflies comparison.

#3 — Notta: wide list, wrong workflow for mixed meetings

Notta supports 58 transcription languages plus real-time translation into roughly 42, and its bilingual side-by-side transcript view is the best in class if your job involves producing documents in two languages. It records from web and mobile, so in-person capture is possible, and it sells a pocket recorder (Notta Memo) if you want dedicated hardware.

What holds it back for *this* use case specifically: there's no automatic language detection — you select the language before recording starts. For a genuinely bilingual meeting that's the wrong shape, because whichever language you pick, the other one suffers. Its free tier also caps sessions at three minutes, its mobile app is a wrapper around the web product rather than a native one, and it has a well-documented trail of billing complaints. Its AI training default uses your data on non-Enterprise plans. Full breakdown in our Notta comparison.

#4–#7 — the rest, and why they rank there

#4 Granola captures system audio on a Mac with no bot in the call, which is excellent if your multilingual meetings happen at a desk on a laptop. Its AI enhances notes you type rather than producing a full standalone translated summary, and on iPhone it can't capture virtual meetings at all. See the Granola comparison.

#5 Fathom has the most generous free plan of anything here and claims 25+ languages. It's online-calls-only, can't import an audio file, and its translation stops at the transcript. Good value, wrong shape for this job. See the Fathom comparison.

#6 tl;dv offers translated transcripts in 30+ languages and is genuinely strong at sales coaching analytics. Its iOS app sits around 2★ and its free plan caps you at 10 AI summaries for the lifetime of the account, which makes it a poor fit for anyone whose multilingual meetings happen away from a desk. See the tl;dv comparison.

#7 Otter.ai is last here for one reason: 6 languages, with no auto-detect and no translation of the summary. English (US and UK), Spanish, French, German, Japanese, and Chinese Simplified. Otter is very good at live English transcription and effectively unusable for most multilingual work. See the Otter.ai comparison.

How to run a two-language meeting end to end

With automatic detection there's far less to set up than most guides suggest. This is the whole workflow in Noter AI.

  1. 1Just start recording. There's no language to choose. In person, start the recording and put the phone on the table — a phone mic handles a normal meeting room fine. For an online call, paste the link or let the bot join from your synced calendar.
  2. 2Let people speak naturally. Nobody has to stick to one language for the tool's benefit, and switching mid-sentence is fine.
  3. 3Check the transcript. Both languages appear as they were spoken, with speaker labels and timestamps. Tap any line to replay that moment in the audio.
  4. 4Translate the output into your reader's language. Choose a target language and the summary, analysis, and action items come through translated. The original is kept, so nothing is lost.
  5. 5Send the summary, not the transcript. That's the part colleagues will actually read.
  6. 6Export and share. PDF for a formatted document, Word if people need to edit, plain text or rich-text copy for pasting into email or Slack.
  7. 7Optional: if you already know which two languages will come up, set them as language hints to squeeze out a little extra accuracy. A refinement, not a requirement.

How to choose

  • Your meeting genuinely mixes two languages → Noter AI or Fireflies. Both auto-detect and handle switching; the others make you commit to one language up front.
  • That mixed meeting happens in a room, not on a call → Noter AI. Fireflies cannot record it at all.
  • You need the summary and action items in the second language, not just the transcript → Noter AI.
  • You need a rare language that isn't in Noter's 60+ → Fireflies, for the 100+ catalogue.
  • You need the finished notes written in an uncommon language → check Noter's 18 translation languages first; if it's not there, Notta or Fireflies.
  • You produce two-column bilingual documents → Notta's side-by-side view.
  • You're on a Mac and don't want a bot in the call → Granola.
  • You need it free → Fathom, accepting that it's online calls only.
  • Your meetings are in English and you want a live scrolling transcript → Otter, and ignore this page.

Bottom line

The language-count number on a pricing page answers a question most people aren't really asking. What matters for a multilingual meeting is whether the app copes without being told what's coming, whether it can record the meeting wherever it happens, and whether the *result* arrives in the language your reader speaks — summary, decisions, and action items included.

On that combination, Noter AI is the strongest option in 2026: 60+ transcription languages with detection always on, mixed-language conversations handled, in-person or virtual capture, and translated summaries — at one flat price. If you need a rare language outside those 60+, Fireflies has the larger catalogue and we'll happily point you there.

Frequently asked questions

What's the best app for transcribing a meeting held in two languages?

Noter AI, in most cases. Its transcription covers 60+ languages with automatic language detection always on, so you don't choose a language before recording and speakers can switch language mid-conversation without wrecking the transcript. It's also the only option that can record a bilingual in-person meeting from a phone and translate the summary and action items — not just the raw transcript. Fireflies is the alternative if you need a rare language outside those 60+, though it can only record online calls.

Do I have to choose the language before I start recording?

Not in Noter AI — automatic language identification is enabled on every recording, so you can just press record. You can optionally supply language hints to bias accuracy toward the languages you expect, but they aren't required. Notta and Otter both require you to pick the language in advance, which is the most common cause of an unusable multilingual transcript.

What happens if people switch between two languages in the same meeting?

Noter AI handles it. The speech model tags language at the word level rather than locking the whole recording to one language, so a conversation that moves between, say, Arabic and English comes back as a single coherent transcript with both rendered correctly. Apps that commit to one language when you press record will transcribe the second language phonetically, producing nonsense.

How many languages does Noter AI support?

Transcription covers 60+ languages with automatic detection. Translation of the finished notes — transcript, summary, analysis, and action items — is available in 18: Arabic, Chinese (Simplified), Chinese (Traditional), Dutch, English, French, German, Indonesian, Italian, Japanese, Korean, Polish, Portuguese, Russian, Spanish, Thai, Turkish, and Vietnamese.

Which app supports the most languages overall?

Fireflies.ai claims 100+ with automatic detection, followed by Noter AI at 60+ (also auto-detected), Notta at 58, Granola and tl;dv at around 30, Fathom at 25+, and Otter.ai at just 6. Raw count isn't the whole story — it says nothing about whether the app can record an in-person meeting, cope with two languages at once, or translate the summary.

Can any of these record a multilingual meeting that isn't on Zoom?

Only three. Noter AI records in person from an iPhone, iPad, or Android phone with one tap. Granola captures system audio on a Mac. Notta can record from web or mobile. Fireflies, Fathom, and Otter are built around a bot joining an online call and cannot capture a conversation in a room; tl;dv's iOS recording exists but is unreliable.

Let Noter AI take your meeting notes

Record, transcribe, and summarize meetings on iPhone, iPad & Android — or send a bot to Zoom, Teams, Meet, or Webex. In 60+ languages.

Related reading