Translate Audio to English
English is the one target you can reach on every plan in a single step. Tick "Transcribe to English" when you start a job and the speech model writes English directly from the source audio, instead of transcribing first and translating afterwards. It's the quickest route when you just need to read a recording in English; if you also want the original-language text, transcribe normally and use Translate instead.
- 134+ Translation languages
- AI transcription
- Encrypted; we never train AI on your files
Start with your recording
Drop an audio or video file here, or click to choose.
Already have subtitles? Translate them here
Upload an SRT, VTT, ASS or other subtitle file, translate it into 134+ languages with Google Translate, and download it with the original timings.
What you get: a real transcript
Unedited output from a 64-second interview with two speakers (synthetic voices), transcribed with speaker detection on. Only the first lines are shown.
SPEAKER_00 (0:00) Welcome back to Small Shop Stories. SPEAKER_00 (0:02) Today I'm talking to Maya, who runs a tiny bakery on the SPEAKER_00 (0:05) corner of Mill Street. SPEAKER_01 (0:07) Thanks for having me. SPEAKER_01 (0:08) It's really small, just two ovens and a counter. SPEAKER_00 (0:12) So how does a normal day start for you?
1 00:00:00,000 --> 00:00:01,680 [SPEAKER_00] Welcome back to Small Shop Stories. 2 00:00:02,160 --> 00:00:05,320 [SPEAKER_00] Today I'm talking to Maya, who runs a tiny bakery on the 3 00:00:05,320 --> 00:00:06,320 [SPEAKER_00] corner of Mill Street.
Checked against the script, 4 of 189 words differed — a 2.1% word error rate, counting "80" written for "eighty" as an error — and all 14 speaker turns were labelled correctly. This was clean speech; noisy recordings and people talking over each other score lower. See the full transcript and how it was scored
How it works
- 1
Upload
Drop in an audio or video file, or paste a link. All common formats are accepted.
- 2
Transcribe
AI transcribes with timestamps and optional speaker labels, usually in minutes.
- 3
Translate
Open the transcript in Google Translate for any of 134+ languages, with every timestamp kept, or tick “Transcribe to English” before you start.
Why ScribeToAny
- Direct single-step audio-to-English translation pipeline powered by specialized Whisper multilingual speech models.
- Works the same from French, Japanese, Korean, Arabic, Russian, Portuguese, Italian and the other ~90 supported languages — check names and key figures against the audio.
- Eliminates intermediate translation friction: transcribes and translates in one unified GPU inference pass.
Frequently asked questions
Is translating to English really free?
Transcribing straight to English is available on every plan, including the free one — it runs inside the speech model itself rather than as a separate translation step. The free plan's normal limits still apply: 2 files a day, 100 minutes a month, 30 minutes per file, no credit card.
What if I need a language other than English?
Translate the finished transcript. Transcribe in the source language, then click Translate: it opens in Google Translate, where you pick any of 134+ languages and save the result back as a subtitle track with the original timings. It is free on every plan.
Which source languages work?
About 98, and you do not have to say which one — the spoken language is detected automatically. Chinese, Spanish, Japanese, Korean, French, German, Portuguese, Hindi, Russian and Arabic all work well, as do most European languages.
Does Transcribe to English keep timestamps?
Yes. The English comes back in timed segments like any transcript, so you can click a line to replay the original audio and export English SRT or VTT subtitles.
Can I get the original-language transcript from the same job?
No — a Transcribe to English job produces English only. If you want both, transcribe in the original language instead, then use Translate to add English as a second track with the same timings.