Skip to content

Italian transcription

Italian audio and video to text

Upload Italian audio or video and get an editable, timestamped transcript you can correct line by line and export as text or subtitles. Standard Italian is well covered by Whisper-family models and regional accents are usually fine, but full dialects such as Neapolitan, Sicilian or Venetian are not Italian to the model and need checking.

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

Regional accents and dialects

Italian sounds very different in Milan, Rome, Naples and Palermo, yet most accents are still recognised as Italian and written with ordinary spelling. The difficulty starts with the dialetti: Neapolitan, Sicilian, Venetian, Sardinian and others have their own vocabulary and often their own grammar, and a speaker who switches mid-sentence produces passages that are wrong. Italian spoken in Ticino or by non-native speakers is generally readable. Mark dialect stretches and check them against the audio.

Accents, apostrophes and double consonants

Written accents carry meaning in Italian: è (is) against e (and), perché, più, città. Check them when you proof-read, because a missing grave or acute accent is easy to overlook. Elisions such as l'anno and un'ora are written as the model hears them, and double consonants are a typical slip in fast speech. The formal Lei and the informal tu follow what the speaker said; the transcript never normalises them.

What speakers of Italian use it for

University students record lezioni and oral-exam revision. Journalists and researchers transcribe interviste. Small firms and studios record riunioni to write up decisions. Many people receive long WhatsApp voice messages (messaggi vocali) and would rather read them. Creators add Italian subtitles to videos for social media. Songs with music under the voice transcribe poorly.

Which model works best for Italian

Italian is one of the languages Whisper-family models have seen the most speech in, so the small model can give a reasonable first draft from clear audio. That is not a promise of accuracy: it still slips on names, numbers, jargon and overlapping or noisy speech, so proof-read anything you will publish or rely on.

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).

Clear single-speaker Italian suits the small model well. Mistakes concentrate in overlapping talk, which is common in Italian conversation and debate, in dialect passages, and where music runs under the voice. Proof-read accents, double consonants and proper names.

Subtitles and captions in Italian

Italian usually runs longer than English for the same meaning, so keep lines to about 37 to 42 characters and two lines at most. Break after a clause, not between an article and its noun, and keep elisions like l'anno together on one line. SRT and VTT are UTF-8, so accented letters display correctly in VLC and YouTube.

The uploader is set to Italian

The upload box on this page transcribes as Italian, 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

Does it transcribe dialects like Neapolitan or Sicilian?
Not reliably. It expects standard Italian, so dialect speech may come back as odd Italian words or errors. Regional accents in standard Italian are much easier than true dialect.
Can it handle Italian WhatsApp voice messages?
Yes, if you save the voice message as a file and upload it. See WhatsApp voice note to text for the steps.
Will accents like è and perché come out correctly?
Usually. The most common slips are è versus e and missing accents on final vowels, so read the transcript once with those in mind.
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.