Transcribe audio to learn a language
Upload a lesson, a podcast episode or a film clip in the language you are learning — or record yourself speaking it in the browser — and try it here, with no account. In an account, every word carries its time: click a line to hear it again, and again, and translate the transcript into your own language to check your understanding.
Upload a file
Audio or video from your device.
Record
Your microphone, recorded in this browser.
Keep this page in front while you record. Switching to another app or locking the screen makes the browser stop the microphone, and what was missed can’t be recovered.
Keep this tab open while you record. If you close it or open another page in it, the recording is lost.
Auto detect can mishandle a recording that switches language.
Free: one recording up to 10 minutes · its transcript to read · no account · deleted after 48 hours
What you get
In an account — free or Pro, with the same features — the transcript comes with:
- Read along, word by word
- Click any line to hear that passage; the transcript follows the audio while it plays, so you hear each word as you read it.
- Translation into your language
- Translate the transcript into the language you think in, and read it beside the original.
- A summary and questions
- Summarise the episode in the shape that fits it, or ask what was said about a topic; the answer points to the passages and the moment in the recording they are in.
- Editing
- Fix what the recogniser misheard — or what you did — in the text, with the audio beside it.
- Who spoke
- In American English, British English and Indian English, the transcript separates the voices into Speaker 1, Speaker 2 and so on; you rename each label once, and the name holds for the whole transcript. In Australian English and Philippine English, it separates them too, on recordings of up to 2 hours. If the separation fails, the transcript comes without speaker labels, and says so.
- Export
- Word (DOCX), TXT, SRT and VTT, on every plan — TXT to paste into your notes or flashcards.
Pick the language you are learning
Choose the language spoken in the recording — the language you are learning — not your own. Transcription works in 82 languages, several of them in regional variants; pick the variant closest to the speaker. For a recording that mixes your language and the language you study, read the note below before you upload.
Every automatic transcript has errors, and they cluster on proper names, numbers and technical terms. Before you quote a passage, click the line and listen: with a time on every word, that check takes seconds. For a learner that cuts the other way too: a word that looks wrong may be the recogniser's error, not the speaker's — or yours. Listen before you memorise. A transcript of your own speaking shows what was understood, not a grade on how you said it.
You can also record in the browser, on a phone or a computer. Keep the page open and the screen on until you stop: a browser can end a recording when the page goes into the background.
Long recordings
Without an account, the trial transcribes up to the first 10 minutes of a recording. On Pro, each file can be up to 8 hours, within the month's included hours; what each plan includes, the pricing page shows. See plans and prices.
On long recordings, speaker labels can wander from one section to the next — a consequence of how long audio is processed, not a setting.
Before you upload
Name the main language rather than leaving it on automatic. Automatic detection has to decide what language each stretch of speech is in, and where a recording switches language, what was said in the other one may come back translated instead of transcribed — or not come back at all. Either way nothing is marked as missing: the transcript will look complete.
Philippine English is marked “preview” in the language list: offered, but without a quality commitment yet, so check its transcript more closely before you use it.
Frequently asked questions
- Does it cost anything to transcribe a lesson?
- To try it, nothing: without an account, the trial transcribes up to the first 10 minutes of a recording, and the result page shows what you can read without paying and how to read the rest. What the free account includes today and Pro's prices are on the pricing page.
- Can I check my pronunciation with it?
- Not as an assessment. What comes back is what the recogniser understood; a misheard word may be its error or yours, and nothing here scores it. It is a way to see what you said and hear it back.
- Does it separate the teacher from the student?
- In American English, British English and Indian English, the transcript separates the voices into Speaker 1, Speaker 2 and so on; you rename each label once, and the name holds for the whole transcript. In Australian English and Philippine English, it separates them too, on recordings of up to 2 hours. If the separation fails, the transcript comes without speaker labels, and says so.
- Which files can I upload?
- Audio or video as it is: we accept MP3, M4A, WAV, OGG, Opus, MP4, MOV and WebM, among others.
- What happens to the recordings I upload?
- Your recordings and transcripts are not used to train models. In the no-account trial, the file and the transcript are deleted 48 hours later — or 7 days after payment, if you buy just that transcript; in an account, they are kept until you delete them.