Catalan voicemails and voice notes, transcribed properly
Catalan (català): Central and Valencian varieties both transcribe on the same model; output uses standard Catalan orthography. Handles the constant Catalan–Spanish code-switching of real recordings; geminated l·l and apostrophes come out correctly.
Voicemails in particular: Short clips process in seconds; numbers and callback details deserve a glance. Readable messages, searchable follow-ups and nothing lost in the inbox.
How it works
Record well
Export or forward the audio file — even 20-second clips are worth it.
Upload it
Drop the file into Whipscribe or paste a link. 30 minutes free daily, no signup to try.
Read & export
Speaker-labeled, timestamped Catalan text in minutes. Export TXT, SRT, VTT, or DOCX.
Typical uses: Municipal plenaries, radio, podcasts and university lectures across Catalonia, Valencia and the Balearics.
Frequently asked
Can Whisper transcribe Catalan voicemails and voice notes?
Yes. Central and Valencian varieties both transcribe on the same model; output uses standard Catalan orthography. Handles the constant Catalan–Spanish code-switching of real recordings; geminated l·l and apostrophes come out correctly.
How are speakers handled in a voicemail?
Short clips process in seconds; numbers and callback details deserve a glance.
How much does it cost?
About 3.3¢ per audio minute (~$2 an hour), 30 minutes free every day, no signup to try.
Is my recording private?
Yes — private infrastructure, never sent to a third-party AI service, no training on uploads. Always get participants' consent before recording.