ScribeToAny

Convert Opus to Text

Opus is the codec behind most voice notes and calls — WhatsApp, Telegram, Discord — which means a lot of what people actually say to each other is locked in .opus files you cannot search. Upload the voice note and ScribeToAny transcribes it into timestamped text you can read, quote and export, with optional speaker labels for a two-person exchange. Works on every plan.

  • AI transcription
  • 98 Languages
  • Encrypted; we never train AI on your files

Start with your recording

Drop an audio or video file here, or click to choose.

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.

Transcript (TXT)
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?
Subtitles (SRT)
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. 1

    Upload

    Drop in an audio or video file, or paste a link. All common formats are accepted.

  2. 2

    Transcribe

    AI transcribes with timestamps and optional speaker labels, usually in minutes.

  3. 3

    Export

    Edit segments online, then export TXT, SRT, VTT, TSV, CSV, JSON, PDF or DOCX.

Why ScribeToAny

  • Engineered for WhatsApp audio notes, Telegram voice messages, and Discord streams encoded in the low-latency Opus codec.
  • Low-bitrate voice notes (often 12–24 kbps) usually transcribe well, since Opus is built for speech; Restore audio helps with background noise.
  • The estimator reads a voice note's length in your browser before you upload, so you know how many minutes it will use.

Frequently asked questions

Can I transcribe WhatsApp or Telegram voice notes?

Yes — export or save the voice note as an .opus (or .ogg) file and upload it here. The audio is transcribed as-is; there is no need to convert it first, and no app to install.

Does it separate two speakers?

Yes. Turn on Detect speakers and the transcript is split by speaker, so a two-person voice note comes back as a labelled back-and-forth rather than one block. It's a best-effort split by voice. Speakers come back numbered rather than named, and the labels can't be renamed in the app yet — if you need real names, find-and-replace them in the exported DOCX or TXT.

What can I do with the transcript?

Edit it in the browser, click a line to replay that moment, then export TXT, SRT, VTT, TSV, CSV, JSON, PDF or DOCX. You can also translate it into 134+ languages for free, on every plan. Translations keep the original timestamps.

Voice notes are heavily compressed — is that a problem?

Usually not. Opus is designed for speech, so even the low bitrates messaging apps use keep words intelligible. What hurts more is wind, traffic or music in the background — turn on Restore audio for those notes, and click a line in the editor to replay anything unclear.

Can I transcribe a batch of voice notes at once?

Yes — select up to 6 files in one upload. The free plan allows 2 transcriptions a day, while paid plans have no daily limit and transcribe up to 6 files in parallel, so a whole thread of voice notes goes through in one go.

Related tools