Skip to content
Translate

Translate audio to English text

Pick a recording in another language and get English text straight from the speech, made on your own device.

  • Nothing uploaded
  • No sign-up
  • Free
or drop it here · MP3 WAV M4A MP4 MKV MOV FLAC OGG
Nothing is uploaded
How it works

Three steps, all on your device

  1. Pick the recording

    Audio or video in any of the supported languages. Translate to English is already on for this file.

  2. English text appears

    A multilingual model listens to the speech and writes it down in English, timed line by line.

  3. Use it as text or subtitles

    Copy the English text, save a document, or export SRT and VTT for English subtitles.

Why it works

Why OmniaScribe

  • From 99 languages

    Speech in any language the multilingual models know can come out in English.

  • Translated on your device

    The recording and the translation never pass through a server.

  • English subtitles in one go

    The translated lines keep their timing, so they export as subtitles.

Speech straight to English

Most translation tools work in two steps: transcribe the speech, then translate the text. Here the multilingual speech model can do both at once. It listens to Spanish, Japanese, Russian or any other language it knows and writes English directly, with each line timed to the moment it was said. That keeps the timing for subtitles and avoids a second pass through a separate translator.

What you need

Translation needs a multilingual model. The English-only models are smaller and very accurate for English, but they cannot translate. When you open the workspace from this page, Translate to English is switched on for this one file; if your selected model is English-only, the workspace says so and you can pick a multilingual one on the Models screen.

Model size matters more for translation than for plain transcription. Fast often gives loose or partial translations. Standard is usable for most widely spoken languages, and High accuracy gives the best English, especially for languages further from English.

What to expect from the English

The result is a faithful working translation, not a polished one. Meaning usually comes through well for clear speech. Idioms are often translated word for word, names may be spelled the English way, and very short lines can lose context. For anything that will be published or used in a legal or medical setting, have a fluent speaker check it. For understanding an interview, a lecture or a video, it is usually more than enough.

Translating into other languages

The speech model translates into English only. For another target language, transcribe in the original language, then use Translate on the result. In Chrome on a computer, the browser’s own on-device translator makes a translated copy with the same timestamps. OmniaScribe never sends the text to an online translation service.

Tips for better translations

Choose the spoken language yourself instead of using detection, especially when the recording starts with music or a greeting in another language. Recordings that switch between languages part-way through are hard to translate cleanly; transcribing each part separately helps. Clear, close speech improves the translation just as it improves a transcript.

When accuracy matters, run the file twice: once as a plain transcript in the original language and once translated to English. Reading the two side by side shows you where a line was translated loosely, and a speaker of the language can check the original quickly because it is already written down and timed.

Specs

Formats and limits

Audio
MP3, WAV, M4A, AAC, FLAC, OGG, OPUS
Video
MP4, MOV, MKV, WEBM
Export
TXT, PDF, DOCX, SRT, VTT
Languages
99, or detect automatically
Longest file per model
ModelComputerPhone
Fast3 h1 h 30 min
Standard2 h1 h
High accuracy1 h30 min

Files that would take more than about 45 min on your device ask before they start.

FAQ

Questions, answered.

Something else on your mind? Email us and a person replies.

Which languages can be translated to English?

Speech in any of the 99 languages the multilingual models know. Quality is best for widely spoken languages.

Does it work with the English-only models?

No. Translation needs a multilingual model. The workspace tells you if yours is English-only.

Is the audio sent to a translation service?

No. The translation is made on your device by the Local AI engine. Nothing is uploaded.

Can I get English subtitles?

Yes. Export SRT or VTT from the result; the English lines keep their timing.

Can I translate into a language other than English?

Transcribe in the original language, then use Translate on the result. That uses the browser’s own translator, available in Chrome on a computer.

Which model should I use?

Standard or High accuracy. Fast works poorly for translation.

How long can the recording be?

On a computer, Fast handles up to 3 h, Standard handles up to 2 h, High accuracy handles up to 1 h. On phones it's half of that.

Guides

OmniScribe for Android

Transcribe anywhere.
No signal needed.

Install the free Android app and turn recordings into text on your phone, even with the screen off. Your audio never leaves the phone.

  • Works offline after a one-time model download
  • Translates offline, too
Get it on Google Playfree with ads · optional Pro
The OmniScribe home screen