Yiddish transcription: an honest view
Yiddish is a low-resource language for the speech model. Expect a rough draft with many corrections, and lines that drift into German or Hebrew. Slow, clear speech from one speaker gives the best result; a crowded room, a recording from a phone in a pocket or singing will need much more work.
A rough draft still helps with long recordings. Click a line to replay it and correct it in place; changes save automatically.
Upload the recording as it is: MP3, M4A, WAV, OGG, OPUS, FLAC or AAC, a voice note saved from WhatsApp or Telegram, or a video file such as MP4 or MOV. You can also record from your microphone in the browser. Long files are split and processed in parallel, so a ten-minute recording usually takes a minute or two.
Spelling and right-to-left text
The transcript is written in the Hebrew alphabet. Yiddish spelling differs between the YIVO standard used in schools and scholarship and the spelling common in Hasidic publications, and the draft does not follow either consistently. Choose the convention you need and apply it while reviewing.
Words of Hebrew and Aramaic origin keep their traditional spelling in Yiddish, and the model may write them phonetically or confuse them. Exports are UTF-8 right-to-left text. YouTube shows RTL subtitles correctly; some desktop subtitle editors misplace punctuation.
Dialects and English, Hebrew and German
Hasidic Yiddish in New York, London and Antwerp is mostly based on Hungarian and Polish varieties, while many archive recordings feature Lithuanian Yiddish. The model will not handle all of them equally, and pronunciations far from its training data need more corrections.
Speakers mix in English, Modern Hebrew or other local languages. Keep Yiddish selected when Yiddish dominates. Auto-detect can label Yiddish as German or Hebrew, which gives the wrong text, so this page sets Yiddish for you.
What people record in Yiddish
Uploads include shiurim and religious talks, oral-history interviews with Holocaust survivors and older relatives, family recordings, lectures, and Yiddish theatre and radio archives. Researchers and learners use the draft to find passages in long recordings.
Exports and next steps
Export TXT or DOCX for notes and documents, PDF for a fixed copy, SRT or VTT for subtitles, and CSV with one row per line and its start time. Timestamps and speaker names can be switched on or off in each export. Speaker labels are available on paid plans or with a Minute Pack.
For video files, such as a recorded shiur or an archive interview, see the Yiddish video to text page.