Transcription for press interviews
Transcribe press interviews to text automatically with AI. Fast, accurate and in 60+ languages. 15 free minutes when you create an account.
00:00Press interviews
Why transcribe press interviews
When you're on deadline you can't spend hours transcribing quotes. Upload the recording, find the exact quote with timestamps and verify it by listening to the original clip.
00:00
A workflow for journalists
- Record the interview or press conference with your phone or recorder, or download the call audio.
- Upload it as soon as you finish: within minutes you'll have the full text.
- Find quotes with search and timestamps.
- Listen to the original clip of each quote before publishing to confirm the exact words.
- Download the Word file and store it with the audio in your source archive.
00:00
Always verify quotes
Automatic transcription is very accurate but not infallible: it can mix up numbers, proper names or similar-sounding words. For a direct quote, the rule is the usual one: listen to the audio. The synced editor makes that instant: click the sentence and that clip plays.
00:00
Protecting sources
- Files are transferred encrypted and deleted automatically after 7 days. They're never used to train models.
- If a source is especially sensitive, you can delete the transcript from your account as soon as you download it.
- Consider anonymizing the file name (e.g. source-A.m4a) before uploading.
00:00
Beyond the interview
The same workflow works for council meetings, press conferences, webinars and conferences, podcasts or social videos you need to quote. When working with many interviews at once, timestamps save the most time.
00:003 steps
How to transcribe in 3 steps
Upload your file
MP3, WAV, M4A, MP4, WhatsApp voice notes… up to 5 hours and 2 GB.
AI transcribes it
Our GPU servers turn speech into text with timestamps.
Review and download
Edit anything you want and export to Word, TXT or subtitles.
00:00Why Sonorarium
Everything you need to turn speech into text
Accuracy from a leading model
We run Whisper large-v3 turbo on GPUs, one of the most accurate speech recognition models available. Accuracy varies with the language and the audio quality.
60+ languages
Automatic language detection, or pick it yourself. Great for English, Spanish, Portuguese and many more.
Really fast
An hour of audio is usually transcribed in just a few minutes.
Export to any format
TXT, Word (DOCX), SRT and VTT subtitles, or JSON with timestamps.
Built-in editor
Listen to the audio in sync with the text and fix any word before downloading.
Private by default
Files are encrypted in transit, automatically deleted after 7 days and never used to train models.
00:00FAQ
Frequently asked questions
Can I transcribe a recorded phone call?
Yes, although phone audio is lower quality and accuracy may be slightly lower. Pay special attention to numbers and names.
What about press conferences with questions from the floor?
Contributions close to the microphone transcribe very well; questions from the back without a mic may come out incomplete.
How do I transcribe press interviews to text?
Upload the file above, choose the language (or leave it on automatic) and click Transcribe. In a few minutes you'll have the text with timestamps, ready to copy or download.
Can I transcribe press interviews for free?
You can try it free: you get 15 minutes when you create an account, no card needed. After that, buy minutes whenever you need them — no subscription and no expiry.
Which formats can I download the transcript in?
TXT, Word (DOCX), SRT and VTT subtitles, and JSON with timestamps.
Is my data safe?
Your files are transferred encrypted, deleted automatically after 7 days and never used to train AI models.