.opus · no conversion needed

Opus to text, no conversion step.

The codec inside most messaging-app voice notes. Drop the .opus file (or a link to one) and get a speaker-labelled, word-timed transcript back in about a minute per half hour of audio.

from $0.36/hour · one-time packs·credits never expire·never used to train AI

About .opus files

Opus at even low bitrates keeps speech intelligible, and transcription quality holds up. Discord recordings and VoIP call exports are typically Opus.

Where .opus files come from

Discord calls, VoIP recordings, messaging-app audio.

What you get

Speaker labels

Multi-voice recordings come back with each speaker separated and labelled.

Word-level timestamps

Every word is timed — accurate SRT/VTT subtitles come straight out.

100+ languages

The language is auto-detected; mixed-language recordings are handled per sentence.

Every export

TXT, SRT, VTT, DOCX and JSON on every pack — no format paywall.

Questions people ask

Do I need to convert .opus to MP3 first?

No. Upload the .opus file exactly as it is — decoding happens server-side, and lossless or original-codec input transcribes better than a re-compressed MP3 anyway.

Is there a size or length limit for .opus files?

Files up to 10 hours each are accepted, and multi-gigabyte uploads resume if your connection blips.

How much does it cost?

The preview is instant with no signup. Credits are one-time purchases that never expire: $4 for 300 minutes, $12 for 2,000 minutes (about 36¢ per hour of audio).

Can I paste a link instead of uploading?

Yes — paste a direct link or a page URL and the audio is fetched server-side, which is faster than uploading from a slow connection.